The ultimate guide to the state of today’s A.I. – Fortune
State Of AI And Machine Learning In 2019
Machine Learning Terms You Can’t Avoid | by Richmond Alake | Towards Data Science
What Machine Learning Trends You Should Watch In 2020

When not to use machine learning or AI | by Cassie Kozyrkov | Towards Data Science
How to tell if AI or machine learning is real | InfoWorld
Debunking the biggest myths about artificial intelligence | Ars Technica
The basics of modern AI—how does it work and will it destroy society this year? | Ars Technica
Artificial general intelligence - Wikiwand
General purpose intelligence: arguing the Orthogonality thesis - Less Wrong
Why autonomous cars won’t be autonomous | Computerworld

An Overview of National AI Strategies – Politics + AI – Medium
There’s a huge difference between AI and human intelligence—so let’s stop comparing them – TechTalks

The 5 best programming languages for AI development | InfoWorld
7 Steps to Mastering Intermediate Machine Learning with Python — 2019 Edition

The deepest problem with deep learning – Gary Marcus – Medium

机器能像人一样思考吗？人工智能（一）机器学习和神经网络 - YouTube
人脸识别啥原理？人工智能（二）卷积神经网络 - YouTube

The term "AI" represents the state of the art technology of archiving it. Currently (as of 2018) it means deep learning with neural network.
Today’s computer science is yesterday’s AI - Movie Mango - Medium

Artificial general intelligence - Wikiwand

AI is any technology that showcases anything that resembles human intelligence (mimics "cognitive" functions).
Machine Learning is a subset of AI that uses mathematical models from data to make decisions.
Machine Learning algorithms are trained on large amount of data to minimize the error between their predictions and the actual ground truth values. Deep Learning is a kind of ML which uses deep neural networks. DNN does not requires feature extraction as needed for other traditional DL methods.

AI:

the science and engineering of making intelligent machines.
Tasks performed by computers that are normally being performed by human beings with the involvement of visual perception, speech recognition, decision-making, and translation between languages.
Rule based; heuristics & evolutionary learning

ML:

Machine learning is an application of Artificial intelligence in which machines learn on their own on the basis of previous experience.
ML could be considered the subset of Artificial intelligence, just a technique to realize Artificial intelligence.
Three types of ML algorithms: supervised learning + unsupervised learning + reinforcement learning
In traditional machine learning (linear or logistic regressions, SMVs, Random Forests and so on), the algorithm is given a set of relevant features to analyze. However, in deep learning, the algorithm is given raw data and decides for itself what features are relevant.
Algorithms that analyze data, learn from it and make informed decisions based on the learned insights.
Supervised:
classification: Decision Trees, Naive Bayes Classifier, Support Vector Machines
regression (predicting numeric answers): Logistic Regression
Unsupervised:
clustering: K-Means, tree-based clustering
association (finding common sequences of objects: coffee and cream, shoes and socks)
reduce dimensionality (projection, feature selection, and feature extraction): principal component analysis, tSNE

Andrew Ng, Chief Scientist at Baidu - YouTube 2015
Andrew Ng - The State of Artificial Intelligence - YouTube 2017
Explaining AI - YouTube
What is machine learning? Software derived from data | InfoWorld ❗!important
Machine learning explained | InfoWorld
Machine learning algorithms explained | InfoWorldr
How to explain deep learning in plain English | The Enterprisers Project
No, Machine Learning is not just glorified Statistics
9 machine learning myths | CIO
What is Artificial Intelligence? - via @codeship | via @codeship
NVIDIA BrandVoice: From Deep Learning To Data Science: Everything You Need To Know data analytics, machine learning, and deep learning
A Few Useful Things to Know about Machine Learning
Data Science’s Most Misunderstood Hero - Towards Data Science
AI research papers – TechTalks

The Artificial Intelligence Wiki | Skymind
Index of Best AI/Machine Learning Resources
How do I learn machine learning? - Quora
ujjwalkarn/Machine-Learning-Tutorials: machine learning and deep learning tutorials, articles and other resources
Marcin Wojnarski's answer to What are some must-know tricks in field of data science that most people are oblivious to? - Quora

How artificial intelligence works - part 1
How artificial intelligence works — part 2 back propagation
How artificial intelligence works — part 3 GAN

A Beginner’s Guide to AI/ML 🤖👶 – Machine Learning for Humans – Medium ❗!important, Machine Learning for Humans ebook
Machine Learning for Humans – Medium
The Best Machine Learning Resources – Machine Learning for Humans – Medium
Learn Machine Learning the Fun Way - Towards Data Science

Machine Learning Demystified - Data Driven Investor - Medium
Getting Started With Machine Learning - Smashing Magazine - Medium
Machine Learning Algorithms. Here’s the End-to-End. | by Matt Przybyla | Towards Data Science

Machine Learning is Fun! – Adam Geitgey – Medium 8 part series
Your First Machine Learning Project in Python Step-By-Step

In supervised learning, the algorithm we are working with learns from labeled data. The goal of a supervised learning algorithm is to make generalizations about input data based upon data that follows a similar pattern.
Unsupervised learning aims to find similar data points in a dataset, in order to identify higher-order structures in the data.
Reinforcement learning is similar to supervised learning with the difference being that we're training a pretend actor in the environment.

Classification is performed by supervised learners. A labeled "training data set" is fed to the algorithm for it to learn the relationship of features and classification.
Clustering is usually a task for unsupervised learners. The algorithm is expected to discover patterns in the data automatically provided the features, grouping the data by the patterns it has discovered.

Machine Learning Theory - Part 1: Introduction
Machine Learning Theory - Part 2: Generalization Bounds
Machine Learning Theory - Part 3: Regularization and the Bias-variance Trade-off
A Visual Introduction to Machine Learning
20 free books to get started with Artificial Intelligence
Free Resources | MarkTechPost

Model Training with Yufeng Guo | Software Engineering Daily

Getting Started with Topic Modeling and MALLET | Programming Historian
The Myth of Text Analytics and Unobtrusive Measurement – the scottbot irregular

A foolproof way to shrink deep learning models | MIT News | Massachusetts Institute of Technology

AI vs Machine Learning

When did Data Science Become Synonymous with Machine Learning? | by Murtaza Ali | Towards Data Science

The Difference Between AI, Machine Learning, and Deep Learning? | NVIDIA Blog
Deep Learning vs. Machine Learning: Beginner’s Guide | Coursera
Machine Learning vs AI: Are They Same? – Hacker Noon ❗!important, clear explanation
Clearly Explained: How Machine learning is different from Data Mining | by Juhi Ramzai | Towards Data Science
What's the difference between data science, machine learning, and artificial intelligence? – Variance Explained
Artificial Intelligence vs. Machine Learning vs. Deep Learning | Towards Data Science ❗!important
Deep Learning vs. Machine Learning | by Michal Hrabia | Towards Data Science
The Difference between Machine Learning and Deep Learning | by Suhas Maddali | Jun, 2022 | Towards Data Science
What’s the Difference between Machine Learning and AI?
Deep learning vs. machine learning: Understand the differences | InfoWorld ❗!important
Deep Learning vs. Machine Learning vs. AI: How Do They Go Together?
Difference between AI vs Machine Learning vs Deep Learning | by Sasha Andrieiev | Becoming Human: Artificial Intelligence Magazine
AI vs. machine learning vs. deep learning: Key differences
Artificial Intelligence Vs Machine Learning Vs Deep Learning
AI vs Machine Learning vs Deep Learning | Edureka
Deep learning vs. machine learning – What’s the difference?

Video

7 Must-See TED Talks On AI And Machine Learning

Alex Wissner-Gross: A new equation for intelligence - YouTube intelligence is a physical system that find ways to maximize future possibility
Jeff Hawkins: How brain science will change computing - YouTube intelligence should be defined by the ability to make prediction, not the traditional Turing Test

How to Make an Auto Rotoscoping Tool With Python - Lesterbanks creating mask for video effects

Courses

7 of the Best Free AI and ML Online Courses
Top 20 free Data Science, ML and AI MOOCs on the Internet.

new fast.ai course: A Code-First Introduction to Natural Language Processing · fast.ai
Practical Deep Learning for Coders, v3 | fast.ai course v3
How I Trained Computer to Learn Calligraphy Styles: Part1

Machine Learning At All Levels On Coursera ❗!important, by Andrew Ng
Machine Learning | Coursera ❗!important, by Andrew Ng
CS50's Introduction to Artificial Intelligence with Python | edX
Deep Learning by deeplearning.ai | Coursera
Machine Learning Andrew Ng Courses | Coursera ❗!important, by Andrew Ng
AI For Everyone | Coursera
“AI For Everyone”: Course Review & Key Takeaways - Ankit Rathi - Medium
Deep Learning | Coursera
Machine Learning - Stanford University | Coursera
AI Demystified: Free 5-Day Mini-Course | Infinite Red Academy

Machine Learning Crash Course | Google Developers ❗!important, TensorFlow
ML Universal Guides | Google Developers

Intro to Machine Learning Course | Udacity
Artificial Intelligence Online Courses | Udacity
Machine Learning | Udacity
Tensorflow free course - Udacity
Foundations of Machine Learning
Deep Learning Explained | Edx Microsoft
Machine Learning with Knowledge Graphs - VideoLectures.NET
Top 5 TensorFlow and ML Courses for Programmers – Hacker Noon
AWS Training and Certification - Machine Learning
IBM Cloud Promotion for Cognitive Class Learners

MIT 6.S191: Introduction to Deep Learning
MIT Introduction to Deep Learning – TensorFlow – Medium

Deep Learning with TensorFlow | Deep Learning Academy

CS231n Winter 2016 - YouTube
Neural Networks and Machine Learning - The Coding Train - YouTube

TensorFlow Tutorials - YouTube
Hvass-Labs/TensorFlow-Tutorials: TensorFlow Tutorials with YouTube Videos

Teaching - CS 229
afshinea/stanford-cs-229-machine-learning: VIP cheatsheets for Stanford's CS 229 Machine Learning

Stanford University CS231n: Convolutional Neural Networks for Visual Recognition

MLOps

Intro to MLOps: ML Technical Debt | by Vincent Tatan | Towards Data Science
Social AI with Hugging Face featuring Clément Delangue from Hugging Face (Practical AI #35) |> Changelog

Ethics

AI at Google: our principles
Responsible AI Practices – Google AI

Doing good data science - O'Reilly Media
ACLU calls for a moratorium on government use of facial recognition technologies | TechCrunch
A Privacy Dustup at Microsoft Exposes Major Problems for A.I.

The battle for ethical AI at the world’s biggest machine-learning conference

Machine Learning, Ethics, and Open Source Licensing (Part I/II)
Machine Learning, Ethics, and Open Source Licensing (Part II/II)

Limits/Is AI intelligent?

Deep Learning Has Limits. But Its Commercial Impact Has Just Begun.
Deep Learning: A Critical Appraisal (PDF)

why AI can't pass this test - YouTube
How Important is IQ? - YouTube
Does IQ Really Measure How Smart You Are? - YouTube
Geoffrey Hinton - Two Paths to Intelligence - YouTube

François Chollet: Measures of Intelligence | Lex Fridman Podcast #120 - YouTube
How to measure human intelligence | Richard Haier and Lex Fridman - YouTube

Singularity

Technological singularity - Wikiwand
The Singularity is Near » Homepage

A.I. For Good
Artificial Intelligence to Help the World - AI for Good Foundation

Symbolic AI

Symbolic artificial intelligence - Wikiwand represented by Lisp

AI winter

AI winter is well on its way – Piekniewski's blog
AI winter – Addendum – Piekniewski's blog

GoodAI

GoodAI Our mission is to develop general artificial intelligence - as fast as possible - to help humanity and understand the universe.

GoodAI | Brain Simulator source

AI bias: 9 questions leaders should ask | The Enterprisers Project
Joy Buolamwini: How I'm fighting bias in algorithms | TED Talk
AI and Bias
Algorithmic Bias: Why And How Do Computers Make Unfair Decisions? | liberties.eu

Explaining Measures of Fairness - Towards Data Science

Performance/Accuracy

Sensitivity and specificity - Wikiwand
10.3 - Sensitivity, Specificity, Positive Predictive Value, and Negative Predictive Value | STAT 507
Calculation of sensitivity, specificity, and positive and negative... | Download Scientific Diagram
Confusion Matrix with Scikit-Learn and Python - Pierian Training

Sensitivity (Recall) = TP/TP+FN
靈敏度代表「真陽性機率」，解釋作檢測出現陽性時，準確度的百份比。
Specificity = TN/TN+FP
特異性代表「真陰性機率」，解釋作檢測出現陰性時，準確度的百份比。
Accuracy = Correct Sample / Total Sample
Precision = TP/TP+FN
F1-Score = 2 * ((Precision * Recall) / (Precision + Recall))
Harmonic mean of precision and recall

How to evaluate the performance of a machine learning model
Understand Classification Performance Metrics - Becoming Human: Artificial Intelligence Magazine

Version Control

Machine Learning Version Control System

How to Version Control your Machine Learning task — I

Data Version Control With Python and DVC – Real Python
Data Version Control: iterative machine learning
Managing and Versioning Machine Learning Models in Python

Why Git and Git-LFS is not enough to solve the Machine Learning Reproducibility crisis

#perfmatters

4 easy steps to improve your machine learning code performance
Optimization Algorithms for Deep Learning - Analytics Vidhya - Medium

Ax · Adaptive Experimentation Platform
Design Optimization with Ax in Python | by Nathan Lambert | Towards Data Science

Model Repository

Models – IBM Developer
Model Zoo - Deep learning code and pretrained models for transfer learning, educational purposes, and more

The Mythos of Model Interpretability - ACM Queue

神力 AI(MANA)-国内最大的 AI 代码平台

Home | TensorFlow Hub
models/official at master · tensorflow/models
models/research at master · tensorflow/models

For Researchers | PyTorch

Hugging Face – On a mission to solve NLP, one commit at a time.

AI quirks (adversarial examples)

Why deep-learning AIs are so easy to fool
Why deep-learning methods confidently recognize images that are nonsense over-interpretation
This AI Does Nothing In Games…And Still Wins! - YouTube
This Image Breaks AI - YouTube

Welcome to the cleverhans blog | cleverhans-blog
tensorflow/cleverhans: An adversarial example library for constructing attacks, building defenses, and benchmarking both
[1610.00768] Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
[1811.03685] New CleverHans Feature: Better Adversarial Robustness Evaluations with Attack Bundling
[1707.08945] Robust Physical-World Attacks on Deep Learning Models

[2307.15043] Universal and Transferable Adversarial Attacks on Aligned Language Models
Adversarial Attacks on LLMs - YouTube

Breaking Machine Learning With Adversarial Examples
How to trick a neural network into thinking a panda is a vulture
Breaking Linear Classifiers on ImageNet
[1412.6572] Explaining and Harnessing Adversarial Examples
!!Con 2016 - How to trick a neural network! By Julia Evans - YouTube
Robust AI: Protecting neural networks against adversarial attacks – TechTalks
How To Trick a Neural Network in Python 3 | DigitalOcean
Tricking AI Image Recognition - Computerphile - YouTube

Specification gaming examples in AI | Victoria Krakovna AI model exploiting design flaws in study
Specification gaming examples in AI - master list

How to tell whether machine-learning systems are robust enough for the real world

Natural Language

voice-assistant
mycroft

Introduction - Hugging Face Course
How Hugging Face is tackling bias in NLP | VentureBeat
The Illustrated Retrieval Transformer – Jay Alammar – Visualizing machine learning one concept at a time.

Everything You Need to Know about Natural Language Processing
5 Heroic Tools for Natural Language Processing | IT Svit Blog
8 great Python libraries for natural language processing | InfoWorld
6 Fundamentals you Should Learn to Kickstart your Natural Language Processing Skills | by Ivo Bernardo | Oct, 2021 | Towards Data Science

LibreTranslate/LibreTranslate: Free and Open Source Machine Translation API. 100% self-hosted, offline capable and easy to setup.
LibreTranslate - Free Open Source Machine Translation API - PART 2 - YouTube
cmooredev/LibreTranslate

Advanced NLP with spaCy · A free online course
Natural Language Processing With spaCy in Python – Real Python

Python Libraries for Natural Language Processing | by Claire D. Costa | Towards Data Science
How to use NLP in Python: a Practical Step-by-Step Example | Towards Data Science
A Guide to Perform 5 Important Steps of NLP Using Python

Google’s sophisticated WaveNet audio processing neural network, and because it intelligently inserts “speech disfluencies”

keon/awesome-nlp: A curated list of resources dedicated to Natural Language Processing (NLP)
Deep Learning for NLP: ANNs, RNNs and LSTMs explained!

Introducing speech-to-text, text-to-speech, and more for 1,100+ languages Meta

jellyfish documentation
jamesturk/jellyfish: 🎐 a python library for doing approximate and phonetic matching of strings.

Talisman - Phonetics
SudachiPy: A Japanese Morphological Analyzer in Python

Ready for a go? Facebook opens PyText NLP framework to all • DEVCLASS

nlp-compromise/nlp_compromise: a cool way to use natural language in javascript
Natural language processing for Node.js - LogRocket Blog

Chatbot

Chatbot Comparison – Facebook, Microsoft, Amazon, and Google | Emerj

A Bot Development and Information Portal - Discover.bot

Microsoft Bot Framework
Deep Learning for NLP: Creating a Chatbot with Keras!

How We Created a Slack Bot for Time Tracking with Vue.js and Ruby on Rails - Codica

Voice Isolation

Google works out a fascinating, slightly scary way for AI to isolate voices in a crowd | Ars Technica

Computer Vision

opencv

A 2019 Guide to Object Detection
DeepSORT: Deep Learning to track custom objects in a video

Face detection is a type of computer vision technology that is able to identify people’s faces within digital images. Uses AdaBoost, Haar-like Features, Vila-Jones Object Detection Framework.

Facial recognition involves identifying the face in the image as belonging to person X and not person Y. It is often used for biometric purposes, like unlocking your smartphone.

Facial analysis tries to understand something about people from their facial features, like determining their age, gender, or the emotion they are displaying.

Facial tracking is mostly present in video analysis and tries to follow a face and its features (eyes, nose, and lips) from frame to frame.

Step-by-Step Tutorial on Image Segmentation Techniques in Python
Step-by-Step Implementation of Mask R-CNN for Image Segmentation
Real Time Image Segmentation Using 5 Lines of Code - KDnuggets

Reverse Image Search with Machine Learning - commercetools tech
Object Detection with Less Than 10 Lines of Code Using Python

Counterfactual World Modeling
Stanford Researchers Introduce CWM (Counterfactual World Modeling): A Framework That Unifies Machine Vision - MarkTechPost

facebookresearch/detectron2: Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

Image Pre processing

Documentation request: CHW and HWC layouts · Issue #276 · microsoft/CNTK
Intel(R) MKL-DNN: Understanding Memory Formats
Image Pre-Processing | Caffe2

Clustering

Unsupervised Learning: Clustering Algorithms - Towards Data Science

K-Nearest Neighbors (kNN) — Explained - Towards Data Science
The Most Comprehensive Guide to K-Means Clustering You'll Ever Need

K-nearest neighbors from scratch - Philipp Muens
K-Means Clustering in Python: A Practical Guide – Real Python

Imbalanced Classification With Python (7-Day Mini-Course)

Minimize sum of intra-cluster distance (inertia)
Maximize inter-cluster distance

categorical variables

It is not advisable to use the ordinal form of categorical variables in clustering, you have to convert them in numeric values which make more sense with rest of the data points, you can use one of the following methods to convert them into numeric form

Use 1-hot encoding (So that one category is not influenced by other numerically)
If you have classification problem, use target encoding to encode the categorical variables
If the categories are ordinal in nature then you may use the label encoding
Find the correlation between the categorical variable and all the numeric variables, now replace the mean of the numeric variable value which has the highest correlation with the categorical variable. Correlation can be found using the one-way ANOVA test.

Forecasting

The Art of Forecasting - Towards Data Science

Prophet | Forecasting at scale.
Python Time Series Forecasting Tutorial - The New Stack

DuHL

Duality-gap based Heterogeneous Learning

IBM Rockets Machine Learning Process by 10 Times
IBM shows off tenfold improvement in machine learning using GPUs - TechSpot
Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems

Three Simple Theories to Help Us Understand Overfitting and Underfitting in Machine Learning Models

Decision Tree

Decision Tree Algorithm, Explained
How to visualize decision trees
How to Create a Perfect Decision Tree - DZone AI
Decision Tree Classification Clearly Explained! - YouTube

Random Forest

3 Reasons to Use Random Forest Over a Neural Network–Comparing Machine Learning versus Deep Learning

Random Forests | SpringerLink
Which one is more important? Be careful before you make decisions with Random Forest
Random Forest Algorithm Clearly Explained! - YouTube

Random Forest Overview. A conceptual overview of the Random… | by Kurtis Pykes | Towards Data Science
Master Machine Learning: Random Forest From Scratch With Python | by Dario Radečić | Apr, 2021 | Towards Data Science
How Random Forests & Decision Trees Decide: Simply Explained With An Example In Python | by Serafeim Loukas | Jun, 2022 | Towards Data Science
How to Develop a Random Forest Ensemble in Python

Fraud Detection Using Random Forest, Neural Autoencoder, and Isolation Forest Techniques

SVM

An Introduction to Support Vector Regression (SVR) - Towards Data Science
Linear SVM Classifier: Step-by-step Theoretical Explanation with Python Implementation | by Tarlan Ahadli | Towards Data Science
Support Vector Machines From Scratch - DEV Community

Support Vector Machine (SVM) in 2 minutes - YouTube
Support Vector Machines - YouTube StatQuest

AutoML

Automated machine learning - Wikiwand
Cloud AutoML - Custom Machine Learning Models | AutoML | Google Cloud
What is automated ML / AutoML - Azure Machine Learning | Microsoft Docs

The Risks of AutoML and How to Avoid Them
representation engineering

Automated Machine Learning using Python3.7: Improving Efficiency in Model Development
AutoML, MLBox, Auto-Sklearn, GridSearchCV, and TPOT

Google's AutoML Zero lets the machines create algorithms to avoid human bias

Deep Image

Demystifying — Deep Image Prior – Towards Data Science

Scoring

A Gentle Introduction to Probability Scoring Methods in Python

Recommendation System

Recommender system - Wikiwand
How to implement a recommender system | InfoWorld
Comprehensive Guide to build Recommendation Engine from scratch
A Complete Guide To Recommender Systems — Tutorial with Sklearn, Surprise, Keras, Recommenders | by Pathairush Seeda | Oct, 2021 | Towards Data Science

Unsupervised/Weakly Supervised Learning

An easy introduction to unsupervised learning with 4 basic techniques use cases

Snorkel
snorkel-team/snorkel: A system for quickly generating training data with weak supervision
An Overview of Weak Supervision · Snorkel
[1711.10160] Snorkel: Rapid Training Data Creation with Weak Supervision
Snorkel — A Weak Supervision System | by Shreya Ghelani | Towards Data Science

Reinforcement Learning

What’s New in Deep Learning Research – Towards Data Science
Reinforcement Learning: A Brief Guide - MATLAB & Simulink

Deep Reinforcement Learning Course

Q-Learning
Brute Force
Genetic Algorithm
The Knapsack Problem & Genetic Algorithms - Computerphile - YouTube

Proximal Policy Optimization, an advanced RL algorithm that requires less data than the General Policy Gradient method

Welcome to Spinning Up in Deep RL! — Spinning Up documentation

deepmind/trfl: TensorFlow Reinforcement Learning

DRL 01: A gentle introduction to Deep Reinforcement Learning

DeepMind Has Quietly Open Sourced Three New Impressive Reinforcement Learning Frameworks
OpenSpiel: A framework for reinforcement learning in games | DeepMind
deepmind/open_spiel: OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Spriteworld | DeepMind
deepmind/spriteworld: Spriteworld: a flexible, configurable python-based reinforcement learning environment
Behaviour Suite for Reinforcement Learning (bsuite) | DeepMind
deepmind/bsuite: bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

Dopamine | dopamine
google/dopamine: Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

ntasfi/PyGame-Learning-Environment: PyGame Learning Environment (PLE) -- Reinforcement Learning Environment in Python.
mgbellemare/Arcade-Learning-Environment: The Arcade Learning Environment (ALE) -- a platform for AI research.

Spinning Up in Deep RL

Gym
Gym Humanoid-v2
openai/gym: A toolkit for developing and comparing reinforcement learning algorithms.
openai/retro: Retro Games in Gym
openai/coinrun: Code for the paper "Quantifying Transfer in Reinforcement Learning"
OpenAI Five Dota2

BlueWhale: Applied Reinforcement Learning · BlueWhale
What’s New in Deep Learning Research – Towards Data Science

Introducing Huskarl: The Modular Deep Reinforcement Learning Framework

lexfridman/deeptraffic: DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.

Home - Keras-RL Documentation
keras-rl/keras-rl: Deep Reinforcement Learning for Keras.
A Start-to-Finish Guide to Building Deep Neural Networks in Keras | by Andre Ye | Analytics Vidhya | Medium

Meta-Reinforcement Learning
Reinforcement Learning from scratch – Insight Fellows Program

Genetic Algorithm

Session 2 - Genetic Algorithms - Intelligence and Learning - YouTube
9: Genetic Algorithms - The Nature of Code - YouTube
Introduction to Evolutionary Algorithms - Towards Data Science
Variational Autoencoders (VAEs) for Dummies - Step By Step Tutorial | Towards Data Science

Table of Contents | Genetic Algorithms in Elixir by Sean Moriarity | The Pragmatic Programmers

DeepMind

Google DeepMind
Google DeepMind - Wikiwand
Google DeepMind - YouTube
Google DeepMind on GitHub

DeepMind losses mount as Google spends heavily to win AI arms race

DeepMind & Google Graph Matching Network Outperforms GNN
DeepMind Proposes a Novel Way to Improve GANs Using Gradient Information
Two rival AI approaches combine to let machines learn about the world like a child

Playing Atari with Deep Reinforcement Learning | DeepMind
Explained Simply: How DeepMind taught AI to play video games

DeepMind’s AI agents exceed ‘human-level’ gameplay in Quake III - The Verge
Capture the Flag: the emergence of complex cooperative agents | DeepMind
An AI crushed two human pros at StarCraft—but it wasn’t a fair fight | Ars Technica
AlphaStar: Mastering the Real-Time Strategy Game StarCraft II | DeepMind

Neural scene representation and rendering | DeepMind
Generative Query Network: 3D reconstruction based on 2D images
像人一样脑补世界！DeepMind 历时一年半搞出 GQN，登上 Science - 动点科技
 像人一样脑补世界！DeepMind 历时一年半搞出 GQN，登上 Science - 动点科技
 Google researchers created an amazing scene-rendering AI | Ars Technica

Beat Atari with Deep Reinforcement Learning! (Part 0: Intro to RL)
Beat Atari with Deep Reinforcement Learning! (Part 1: DQN)
Beat Atari with Deep Reinforcement Learning! (Part 2: DQN improvements)

This New Atari-Playing AI Wants to Dethrone DeepMind
DeepMind's Eerie Reimagination of the Animal Kingdom

【亦】唠唠 AlphaCode：AI 会写代码了，人类怎么办？2022 新年闲唠 - YouTube AI cannot "think different"

Evolutionary Algorithm

How Machines Learn - YouTube
Evolution Simulators - YouTube

Digital Evolution with Joel Lehman, Dusan Misevic, and Jeff Clune - Software Engineering Daily
[1803.03453] The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Evolutionary algorithm outperforms deep-learning machines at video games - MIT Technology Review
New AI improves itself through Darwinian-style evolution - Big Think

Bayesian learning

Supervised Classification: The Naive Bayesian Returns to the Old Bailey | Programming Historian
Neural Networks from a Bayesian Perspective - KDnuggets
How to learn from uncertainty using probabilistic machine learning?

Playing Games

mgbellemare/Arcade-Learning-Environment: The Arcade Learning Environment (ALE) -- a platform for AI research.

How to get better at video games, according to babies - Brian Christian - YouTube weight on novelty

MineDojo | Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Learning to Play Minecraft with Video PreTraining (VPT)
看了 7 萬小時 YouTube 影片，OpenAI 新 IDM AI 模型學會玩《當個創世神》 | TechNews 科技新報

格斗之王！AI 写出来的 AI 竟然这么强！ - YouTube
linyiLYi/street-fighter-ai: This is an AI agent for Street Fighter II Champion Edition.

Making AI Play Lots of Videogames Could Be Huge (No, Seriously) | WIRED
AI's Game Playing Challenge - Computerphile - YouTube

AI Learns to Play Super Mario Bros! - YouTube
AI Learns To Play Super Mario Bros Using A Genetic Algorithm And Neural Network | Chrispresso - All things programming, all things AI

Python Plays: Grand Theft Auto V - YouTube
Python AI in StarCraft II - YouTube

OpenAI Five
OpenAI’s Long Pursuit of Dota 2 Mastery – SyncedReview – Medium history
OpenAI’s Dota 2 defeat is still a win for artificial intelligence - The Verge
Why gaming AI won’t help make AI work in the real world—but could | InfoWorld

Emergent Tool Use from Multi-Agent Interaction
OpenAI Tried to Train AI Agents to Play Hide-And-Seek but Instead They Were Shocked by What They Learned multi-agent reinforcement learning (MARL)
OpenAI Plays Hide and Seek…and Breaks The Game! 🤖 - YouTube

Open-Ended Learning Leads to Generally Capable Agents | DeepMind
Generally capable agents emerge from open-ended play | DeepMind
DeepMind’s AI Plays Catch…And So Much More! 🤖 - YouTube

AlphaGo - The Movie | Full Documentary - YouTube

【亦】警惕 AI 外挂！我写了一个枪枪爆头的视觉 AI，又亲手“杀死”了它 - YouTube

UnityML

Make a more engaging game w/ ML-Agents | Machine learning bots for game development | Reinforcement learning | Unity
Learn how to use Unity Machine Learning Agents - Unity
Unity-Technologies/ml-agents: Unity Machine Learning Agents Toolkit

Unity ML-Agents Course

Mario

MarI/O - Machine Learning for Video Games - YouTube
MarI/O Followup: Super Mario Bros, Donut Plains 4, and Yoshi's Island 1 - YouTube
MariFlow - Self-Driving Mario Kart w/Recurrent Neural Network - YouTube
MarIQ -- Q-Learning Neural Network for Mario Kart -- 2M Sub Special - YouTube

Project Malmo

Project Malmo - Microsoft Research
Microsoft/malmo: Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft.

The Malmo Collaborative AI Challenge - Microsoft Research

Deep Learning

opencv

Deep Learning = Artificial Neural Networks with more than 1 hidden layers

Machine Learning Zero to Hero (Google I/O'19) - YouTube
Machine learning - Wikiwand
Artificial neural network - Wikiwand
Machine Learning Mastery
Neural networks and deep learning

“影分身之术”！训练 50 亿次的 AI 能有多智能 - YouTube
How neural networks work—and why they’ve become a big business – Ars Technica
Early Bird uses 10 times less energy to train deep neural networks look for key network connectivity patterns early in training

Hacker's guide to Neural Networks
Neural Networks: Everything you Wanted to Know - Towards Data Science
The Path to Understanding Machine Learning – The Startup – Medium
A Beginners Guide to Deep Learning – Kumar Shridhar – Medium
Deep Learning made easy with Deep Cognition - Becoming Human: Artificial Intelligence Magazine
A Beginner’s Guide to Deep Learning | by Isabella Lindgren | Towards Data Science
A “weird” introduction to Deep Learning - Towards Data Science
Under the Hood of Deep Learning - Towards Data Science
A New Link to an Old Model Could Crack the Mystery of Deep Learning | Quanta Magazine why large model don't overfit

Deep Learning Made Easy: Part 1: Introduction to Neural Networks | by Sachin Kumar | Towards Data Science
Deep Learning Made Easy: Part 2: Neural Networks with Gradient Descent | by Sachin Kumar | Towards Data Science
Deep Learning Made Easy: Part 3: Activation Functions, Parameters and Hyperparameters and Weight Initialization | by Sachin Kumar | Towards Data Science

Using a deep learning neural network to allow a car to learn to drive itself in just 20 minutes
Wayve — Learning to drive in a day.

Projects - LF Deep Learning

Structuring Ml Concepts – Towards Data Science
Processing Unlabeled Data in Machine Learning - Towards Data Science

Natural vs Artificial Neural Networks - Becoming Human: Artificial Intelligence Magazine
Andrew Ng: Deep Learning, Self-Taught Learning and Unsupervised Feature Learning - YouTube
Training a Neural Network explained - YouTube
How Deep Neural Networks Work - YouTube
The Mathematics of Neural Networks - YouTube
Neural networks - YouTube 3Blue1Brown
Series on Neural Networks - YouTube Luis Serrano
Beginner Introduction to Neural Networks - YouTube giant_neural_network
Neural networks class - Université de Sherbrooke - YouTube Hugo Larochelle
Neural Networks and Machine Learning - YouTube The Coding Train

The Backpropagation Algorithm Demystified – Nathalie Jeans – Medium
Understanding Backpropagation as Applied to LSTM

Start Here With Machine Learning
Deep Learning: A Free Mini-Course - YouTube

Is deep learning overhyped? - Quora
ChristosChristofidis/awesome-deep-learning: A curated list of awesome Deep Learning tutorials, projects and communities.
humphd/have-fun-with-machine-learning: An absolute beginner's guide to Machine Learning and Image Classification with Neural Networks
machinelearningmindset/deep-learning-ocean: All You Need to Know About Deep Learning - A kick-starter

Neural networks and deep learning
Deep Learning Book
Manning | Deep Learning with Python
iamtrask/Grokking-Deep-Learning: this repository accompanies my forthcoming book "Grokking Deep Learning"
Free Book: Statistics -- New Foundations, Toolbox, and Machine Learning Recipes - Data Science Central

What is deep learning, and why should you care? - O'Reilly Radar
What deep learning really means | InfoWorld

feature extraction is done mostly in deep learning process

Data in, intelligence out: Machine learning pipelines demystified | InfoWorld
Do You Know The Difference Between Data Analytics And AI Machine Learning?
Data validation for machine learning – the morning paper
Validating your Machine Learning Model - Towards Data Science
This Image is Red - By Baptiste Coulange

Hands On Machine Learning and its related books
3 Machine Learning Books that Helped me Level Up | Data Stuff
5 machine learning tools to ease software development | InfoWorld

Why does Deep Learning work? | Machine Learning
Why Deep Learning Works II: the Renormalization Group | Machine Learning
The Neural Network Zoo - The Asimov Institute different types of NN
A Mythic Approach to Deep Learning Inference

Music Deep Learning with Feynman Liang | Software Engineering Daily

Deep Neural Networks (Part VII). Ensemble of neural networks: stacking - MQL5 Articles

EnVision: The Black Magic of Deep Learning - Tips and Tricks for the practitioner
Dropout: A simple and effective way to improve neural networks - VideoLectures.NET
Speeding up Convolutional Neural Networks - DEV Community 👩‍💻👨‍💻
Why it’s Not Difficult to Train A Neural Network with a Dynamic Structure Anymore! – Medium
Three pitfalls to avoid in machine learning
Why do Convolutional Neural Networks work so well? - YouTube

How to build your own Neural Network from scratch in Python
On Implementing Deep Learning Library from Scratch in Python
Neural Network Embeddings Explained – Towards Data Science discrete variables to vector of real numbers
The mostly complete chart of Neural Networks, explained ❗!important

Deep Learning & Artificial Intelligence, Pt. I | Curious Minds Podcast - Curious Minds Podcast

History

How neural networks work—and why they’ve become a big business – Ars Technica
How computers got shockingly good at recognizing images – Ars Technica

The researcher behind AI's biggest breakthrough has moved on from Google — Quartz
ImageNet: the data that spawned the current AI boom — Quartz

Conv2d: Finally Understand What Happens in the Forward Pass | by ⭐Axel Thevenot | Towards Data Science

Analog ANN

運算速度比NVIDIA輝達GPU快數百倍！？新對手：類比人工智慧Analog AI，性能超越圖形處理器GPU！它將如何影響人工智慧AI產業呢？ - YouTube

Math

Programming, Math, and Statistics You Need to Know for Data Science and Machine Learning

The Actual Difference Between Statistics and Machine Learning
Statistics versus machine learning | Nature Methods
Mathematics behind Machine Learning – The Concepts you Need to Know
Deep Dive into Math Behind Deep Networks – Towards Data Science
The Blunt Guide to Mathematically Rigorous Machine Learning
Learning Math For Machine Learning And Artificial Intelligence Programming
Foundations of ML: Parameterized Functions - Towards Data Science
The mathematics of optimization for deep learning - Towards Data Science
The Maths behind Back Propagation - Towards Data Science
HSIC bottleneck: An alternative to Back-Propagation

Why are neural networks so powerful? - Towards Data Science
The statistical foundations of machine learning - Towards Data Science

Gradient descent - Wikiwand
Stochastic Gradient Descent Algorithm With Python and NumPy – Real Python

Medical

Medical Imaging Training Techniques
Artificial Intelligence Makes Bad Medicine Even Worse
The Case Against Early Cancer Detection | FiveThirtyEight
Early screening leads to unnecessary treatments to benign cases

A deep learning system accurately classifies primary and metastatic cancers using passenger mutation patterns | Nature Communications
Don't trust deep-learning algos to touch up medical scans: Boffins warn 'highly unstable' tech leads to bad diagnoses • The Register

Transfer Learning

Deep learning made easier with transfer learning
What is Transfer Learning? - KDnuggets

Distillation of Knowledge in Neural Networks - Towards Data Science

PyTorch, Keras

CNN

什么是卷积神经网络？卷积到底卷了啥？ - YouTube

Understanding Neural Networks. From neuron to RNN, CNN, and Deep Learning ❗!important
CNN Explainer
Gentle Dive into Math Behind Convolutional Neural Networks
Introduction to Convolutional Neural Network (CNN) using Tensorflow
Step by Step Implementation: 3D Convolutional Neural Network in Keras

Beginner’s Crash Course to Deep Learning and CNNs - YouTube
Beginner’s Crash Course to Deep Learning and CNNs - Towards Data Science

Let’s Code Convolutional Neural Network in plain NumPy

ResNet, AlexNet, VGGNet, Inception: Understanding various architectures of Convolutional Networks – CV-Tricks.com

Regression with Keras - PyImageSearch
Keras, Regression, and CNNs - PyImageSearch
Keras Tutorial: Develop Your First Neural Network in Python Step-By-Step

Classifying breast cancer tumour type using Convolutional Neural Network (CNN — Deep Learning)

RNN

The Unreasonable Effectiveness of Recurrent Neural Networks
karpathy/char-rnn: Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Crash Course in Recurrent Neural Networks for Deep Learning
Deep Learning for NLP: ANNs, RNNs and LSTMs explained!
Illustrated Guide to Recurrent Neural Networks: Understanding the Intuition
Fundamentals of Deep Learning – Introduction to Recurrent Neural Networks
Building a LSTM by hand on PyTorch - Towards Data Science
Explaining RNNs without neural networks

Long Short Term Memory (LSTM), a unit in a Recurrent Neural Network (RNN) proficient at remembering information for long periods of time and well-suited to classifying, processing and making predictions based on time series data.

Recurrent Neural Networks by Example in Python - Towards Data Science
WillKoehrsen/recurrent-neural-networks: Learning about and doing projects with recurrent neural networks
recurrent-neural-networks/Quick Start to Recurrent Neural Networks.ipynb at master · WillKoehrsen/recurrent-neural-networks
recurrent-neural-networks/Deep Dive into Recurrent Neural Networks.ipynb at master · WillKoehrsen/recurrent-neural-networks

Explainable AI

What-If Tool
Google AI Blog: The What-If Tool: Code-Free Probing of Machine Learning Models

Explainable AI: Peering inside the deep learning black box | InfoWorld
tensorflow/model-analysis: Model analysis tools for TensorFlow
Responsible AI Practices – Google AI

Verifying AI 'Black Boxes' - Computerphile - YouTube masking features rather than reversing the network

manifold demo
Manifold: A Model-Agnostic Visual Debugging Tool for Machine Learning at Uber | Uber Engineering Blog
Open Sourcing Manifold, a Visual Debugging Tool for Machine Learning | Uber Engineering Blog
Uber open-sources Manifold, a visual tool for debugging AI models | VentureBeat

f-dangel/cockpit: Cockpit: A Practical Debugging Tool for Training Deep Neural Networks
Hands-on Guide to Cockpit: A Debugging Tool for Deep Learning Models

investigating node like cells
Zoom In: An Introduction to Circuits
OpenAI Microscope / Models
OpenAI launches Microscope to visualize the neurons in popular machine learning models | VentureBeat

Interpretable Machine Learning – Towards Data Science
Interpretable Machine Learning ❗!important, book

Introducing AI Explainability 360 | IBM Research Blog
aix360 · PyPI
IBM offers explainable AI toolkit, but it’s open to interpretation | ZDNet

What is explainable artificial intelligence? – TechTalks
Explainable AI: Viewing the world through the eyes of neural networks – TechTalks

Hands-on Machine Learning Model Interpretation – Towards Data Science
Deep Learning & Artificial Neural Networks: Solving The Black Box Mystery | Hacker Noon
Easily visualize Scikit-learn models’ decision boundaries | by Tirthajyoti Sarkar | Towards Data Science

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) – Google AI
This is especially important in the development of AI. Through a new research approach called TCAV—or testing with concept activation vectors—we’re working to address bias in machine learning and make models more interpretable. For example, TCAV could reveal if a model trained to detect images of “doctors” mistakenly assumed that being male was an important characteristic of being a doctor because there were more images of male doctors in the training data. We’ve open-sourced TCAV so everyone can make their AI systems fairer and more interpretable, and we’ll be releasing more tools and open datasets soon.
TCAV: Interpretability Beyond Feature Attribution – Towards Data Science

SeldonIO/alibi: Algorithms for monitoring and explaining machine learning models

Coding Deep Learning for Beginners

Coding Deep Learning for Beginners — Start! – Towards Data Science
Coding Deep Learning For Beginners — Types of Machine Learning
Coding Deep Learning for Beginners — Linear Regression (Part 1): Initialization and Prediction
Coding Deep Learning for Beginners — Linear Regression (Part 2): Cost Function
Coding Deep Learning for Beginners — Linear Regression (Part 3): Training with Gradient Descent
FisherKK/F1sherKK-MyRoadToAI: Repository for storing and tracking my self-study progress.

Generative Network

Survival Analysis

estimate death in biological organisms or failure in mechanical systems

Deep Learning for Survival Analysis - Towards Data Science

DL Frameworks

2020-04 PyTorch 1.5
2019-09 TensorFlow 2.0

Pytorch vs. Tensorflow: Deep Learning Frameworks 2021 | Built In 2021-12
PyTorch vs TensorFlow for Your Python Deep Learning Project – Real Python 2020-09
TensorFlow or PyTorch? which is the best? | Towards Data Science 2020-04 PyTorch 1.5
TensorFlow vs PyTorch: The battle continues | by Jordi TORRES.AI | Towards Data Science 2020-04 PyTorch 1.5
TensorFlow or PyTorch? which is the best? | Towards Data Science 2020-04

Pipeline

Model Server: The Critical Building Block of MLOps – The New Stack

MLflow - A platform for the machine learning lifecycle | MLflow
MLflow: An Open Platform to Simplify the Machine Learning Lifecycle

metaflow-ai

Kubernetes:
kubeflow/kubeflow: Machine Learning Toolkit for Kubernetes
TensorFlow in Kubernetes in 88 MB - DZone Cloud
Getting Started with Machine Learning using TensorFlow and Docker – Code with Dan Blog
Kubeflow: TensorFlow on Kubernetes with David Aronchick - Software Engineering Daily

KServe | Kubeflow originally KFServing
KServe: A Robust and Extensible Cloud Native Model Server – The New Stack

Machine Learning Deployment Platform for Enterprise — Seldon
SeldonIO/seldon-core: Machine Learning Deployment for Kubernetes

Introducing Nauta: A Distributed Deep Learning Platform for Kubernetes* - Intel AI

Comparison

The State of Machine Learning Frameworks in 2019
Deep Learning Comp Sheet: Deepleafrning4j vs. Torch vs. Theano vs. Caffe vs. TensorFlow vs. MxNet vs. CNTK - Deeplearning4j: Open-source, Distributed Deep Learning for the JVM
Cheat Sheets for AI, Neural Networks, Machine Learning, Deep Learning & Big Data

Deep Learning Framework Power Scores 2018 – Towards Data Science
zer0n/deepframeworks: Evaluation of Deep Learning Frameworks
Review: The best frameworks for machine learning and deep learning | InfoWorld
Deep learning frameworks: PyTorch vs. TensorFlow | InfoWorld
Is TensorFlow better than other leading libraries such as Torch/Theano? - Quora

CNTK

Microsoft Cognitive Toolkit
The Microsoft Cognitive Toolkit - Cognitive Toolkit - CNTK | Microsoft Docs
Reasons to Switch from TensorFlow to CNTK | Microsoft Docs

ONNX

ONNX Open Neural Network Exchange Format
Open Neural Network Exchange - Wikiwand
ONNX allows developers to move models between frameworks such as CNTK, Caffe2, MXNet, and PyTorch.

onnx/onnx: Open Neural Network Exchange

TensorFlow

PyTorch is replacing TensorFlow in 2022?

TensorFlow -- an Open Source Software Library for Machine Intelligence
Why TensorFlow for Python is dying a slow death

Official Google Blog: TensorFlow: smarter machine learning, for everyone
Research Blog: TensorFlow
Google Announces TensorFlow Graphics Library for Unsupervised Deep Learning of Computer Vision Model
Cheat sheet: TensorFlow, an open source software library for machine learning - TechRepublic

The Ultimate Beginner Guide to TensorFlow - Towards Data Science
Explained: Deep Learning in Tensorflow — Chapter 0 - Towards Data Science
Explained: Deep Learning in Tensorflow — Chapter 1 - Towards Data Science

10 Free Resources of TensorFlow One Must Learn In 2020
From Tensorflow 1.0 to PyTorch & back to Tensorflow 2.0
Deep Learning from Scratch and Using Tensorflow in Python
TensorFlow Dev Summit 2019 - YouTube
TensorFlow at Google I/O 2019 - YouTube
Getting Started with TensorFlow 2.0 (Google I/O'19) - YouTube
Learn TensorFlow 2.0 to Build Deep Learning Applications | Udacity
Practical Coding in TensorFlow 2.0 - Towards Data Science
Getting Started with TensorFlow 2.0 (Google I/O'19) - YouTube
Python TensorFlow for Machine Learning – Neural Network Text Classification Tutorial - YouTube 2022

Python is Insufficient for Data Science! That's Why Google has Swift

Coding TensorFlow - YouTube
TensorFlow - YouTube
TensorFlow for Computer Vision - YouTube

TF 1.0 flags:

tf.enable_eager_execution()
session.run
tf.placeholder
feed_dict

pip3 install tensorflow
python3 -c "import tensorflow as tf; tf.enable_eager_execution(); print(tf.reduce_sum(tf.random_normal([1000, 1000])))"

How to check CUDA version in TensorFlow - gcptutorials

python3 -c "import tensorflow as tf; print(tf.sysconfig.get_build_info())"

import tensorflow as tf
sys_details = tf.sysconfig.get_build_info()

Multi GPU, multi process with Tensorflow - Towards Data Science
Quantum Convolutional Neural Network | TensorFlow Quantum

What is TensorFlow? | Opensource.com
TensorFlow 101 (Really Awesome Intro Into TensorFlow) - YouTube
TensorFlow Archives - Software Engineering Daily
Intro to Google Colab, free GPU and TPU for Deep Learning - YouTube

Review: TensorFlow shines a light on deep learning | InfoWorld
What is TensorFlow? The machine learning library explained | InfoWorld
Get started with TensorFlow | InfoWorld
Google’s machine-learning cloud pipeline explained | InfoWorld
TensorFlow tutorial: Get started with TensorFlow machine learning | InfoWorld
Building A Collaborative Filtering Recommender System with TensorFlow

Python:
TensorFlow Neural Network Tutorial
TensorFlow: Save and Restore Models

JavaScript:
TensorFlow.js | TensorFlow
tensorflow/tfjs: A WebGL accelerated JavaScript library for training and deploying ML models.
ml5js · Friendly Machine Learning For The Web.
TensorFlow.js puts machine learning in the browser | InfoWorld
First steps with TensorFlow.js - DEV Community 👩‍💻👨‍💻
Machine Learning For Front-End Developers With Tensorflow.js — Smashing Magazine
Play Street Fighter with body movements using Arduino and Tensorflow.js - DEV Community 👩‍💻👨‍💻
Google’s Deeplearn.js brings machine learning to the browser | InfoWorld
Let's build a game with Tensorflow.js in 10 minutes 🎮 - DEV Community 👩‍💻👨‍💻
Optimizing Face Detection on your browser with Tensorflow.js | by Siddhant Baldota | Towards Data Science

Ecosystem

Keras building neural network
Code examples
An Introduction to Keras Preprocessing Layers — The TensorFlow Blog
First contact with Deep Learning, practical introduction with Keras free ebook
Keras Transfer Learning For Beginners – Towards Data Science
Practical Text Classification With Python and Keras – Real Python
ktrain: A Lightweight Wrapper for Keras to Help Train Neural Networks
Keras Learning Rate Finder - PyImageSearch
4 Awesome things you can do with Keras and the code you need to make it happen
Building a Deep Image Search Engine using tf.Keras - Towards Data Science
Keras with TensorFlow Course - Python Deep Learning and Neural Networks for Beginners Tutorial - YouTube
pop-os/tensorman: Utility for easy management of Tensorflow containers
Reducing Tensorflow Debugging Time by 90 Percent - Towards Data Science
The Google’s 7 steps of Machine Learning in practice: a TensorFlow example for structured data | by B. Chen | Towards Data Science

Ludwig
Introducing Ludwig, a Code-Free Deep Learning Toolbox | Uber Engineering Blog

Project Bonsai for autonomous systems – Microsoft AI
New AI language hides TensorFlow complexity | InfoWorld

Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2 - Stack Overflow
Bash script for local building TensorFlow on Mac/Linux with all CPU optimizations (default pip package has only SSE)
lakshayg/tensorflow-build: TensorFlow binaries supporting AVX, FMA, SSE

TFX | TensorFlow TensorFlow Extended (TFX) is an end-to-end platform for deploying production ML pipelines
TensorBoard | TensorFlow
TensorBoard.dev - Upload and Share ML Experiments for Free
Tensorboard Tutorial - Visualize the Model Performance During Training

Serving Models | TFX | TensorFlow
tensorflow/serving: A flexible, high-performance serving system for machine learning models
How to deploy TensorFlow models to production using TF Serving

Introducing tf-explain, Interpretability for TensorFlow 2.0
sicara/tf-explain: Interpretability Methods for tf.keras models with Tensorflow 2.0

TensorFlow Runtime (TFRT)

TFRT: A new TensorFlow runtime — The TensorFlow Blog
Google Open-Sources New Higher Performance TensorFlow Runtime

PyTorch

PyTorch
PyTorch - Wikiwand

MONAI - Home

How Nvidia’s CUDA Monopoly In Machine Learning Is Breaking - OpenAI Triton And PyTorch 2.0

Ecosystem Day 2021 | PyTorch
facebookincubator/AITemplate: AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

OpenAI→PyTorch
OpenAI goes all-in on Facebook's Pytorch machine learning framework | VentureBeat

Torch | Scientific computing for LuaJIT.
Torch (machine learning) - Wikiwand
torch/torch7: http://torch.ch
torch/cutorch: A CUDA backend for Torch7

Accelerate
How 🤗 Accelerate runs very large models thanks to PyTorch

Start Locally | PyTorch
Opinionated and open machine learning: The nuances of using Facebook's PyTorch | ZDNet
A first look at Pytorch 1.0 – Towards Data Science
9 Tips For Training Lightning-Fast Neural Networks In Pytorch

Introduction to Distributed Training in PyTorch - PyImageSearch
Training an object detector from scratch in PyTorch - PyImageSearch

A Beginner-Friendly Guide to PyTorch and How it Works from Scratch
How to build Convolutional Neural Networks in PyTorch?

Facebook launches 3D deep learning library for PyTorch | VentureBeat
zalandoresearch/flair: A very simple framework for state-of-the-art Natural Language Processing (NLP)

Ecosystem

fast.ai · Making neural nets uncool again
Fast.ai's software could radically democratize AI | ZDNet
do for PyTorch what Keras did for TensorFlow

Announcing TorchServe, An Open Source Model Server for PyTorch | AWS News Blog
pytorch/serve: Model Serving on PyTorch

MXNet

MXNet: A Scalable Deep Learning Framework

Theano

Welcome — Theano documentation

Theano allows you to define, optimize, and evaluate mathematical computations comprising multi-dimensional arrays. It is one of the best python tools loaded with features like tight integration with NumPy, transparent use of GPU, efficient symbolic differentiation, speed and stability optimizations, dynamic C code generation, and extensive unit-testing, to name a few. Theano is well-known for building Deep Learning Projects. Programmers should consider this tool for python development.

DSSTNE

amznlabs/amazon-dsstne: Deep Scalable Sparse Tensor Network Engine (DSSTNE) is an Amazon developed library for building Deep Learning (DL) machine learning (ML) models
DSSTNE, pronounced “destiny”, optimizes for data sparseness and scalability and focuses on optimal use of multiple GPUs

Caffe

Both Caffe and Caffe2 are deprecated
Caffe2 and PyTorch join forces to create a Research + Production platform PyTorch 1.0 | Caffe2

Caffe | Deep Learning Framework
BVLC/caffe: Caffe: a fast open framework for deep learning.

Caffe2 | A New Lightweight, Modular, and Scalable Deep Learning Framework

AI Model Security

trailofbits/awesome-ml-security

Edge AI

When doing inference on edge, the model can be optimized for the target platform (at the cost of prediction performance)

Measuring Machine Learning - Towards Data Science presentation
Benchmarking Edge Computing - Alasdair Allan - Medium blog, ❗!important
Benchmarking TensorFlow Lite on the New Raspberry Pi 4, Model B ❗!important, updated

Why the Future of Machine Learning is Tiny « Pete Warden's blog
Neural network 2.0: a major breakthrough in edge computing AI processing elements (AIPEs) will replace multiply-accumulate (MAC)-based operations

TensorFlow 1.9 Officially Supports the Raspberry Pi

NVIDIA TensorRT

NVIDIA TensorRT | NVIDIA Developer
How to Speed Up Deep Learning Inference Using TensorRT | NVIDIA Developer Blog introductory blog post
TensorRT 4 Accelerates Neural Machine Translation, Recommenders, and Speech | NVIDIA Developer Blog
NVidia 2017 - Washington D.C.
Accelerating Inference In TF-TRT User Guide :: Deep Learning Frameworks Documentation
tensorflow/tensorrt: TensorFlow/TensorRT integration
NVIDIA-AI-IOT/tf_trt_models: TensorFlow models accelerated with NVIDIA TensorRT

Object Detection on GPUs in 10 Minutes | NVIDIA Developer Blog

TensorFlow lite

TensorFlow Lite | TensorFlow
TensorFlow Lite converter | TensorFlow Lite | TensorFlow

How to Deploy Machine Learning Models on Mobile and Embedded Devices
Comparing MobileNet Models in TensorFlow | by Harshit Dwivedi | Heartbeat

A Beginner’s Introduction To TensorFlow Lite - Towards Data Science
TensorFlow Lite Now Faster with Mobile GPUs (Developer Preview)
PINTO0309/Tensorflow-bin: Prebuilt binary with Tensorflow Lite enabled (native build). For RaspberryPi / Jetson TX2 / Jetson Nano. And, solved Tensorflow issues #15062,#21574,#21855,#23082,#25120,#25748.

Google AIY

AIY Projects
Voice requires Google Assistant
Vision
google/aiyprojects-raspbian: API libraries, samples, and system images for AIY Projects (Voice Kit and Vision Kit)

Hacking the Google AIY Voice Kit - Part 1 - YouTube
Hacking the Google AIY Voice Kit Part 2 - Voice Control - YouTube

Voice
Google AIY Voice Kit for Raspberry Pi ID: 3602 - $24.95 : Adafruit Industries, Unique & fun DIY electronics and kits

How to build a smart RasPi Bot with Cloud Vision and Speech API - Google I/O 2016 - YouTube

Federated Learning

NVIDIA FLARE — NVIDIA FLARE 2.2.1 documentation
NVIDIA/NVFlare: NVIDIA Federated Learning Application Runtime Environment

Coral USB Accelerator/TPU

Google Details Tensor Chip Powers IEEE Spectrum - IEEE Spectrum

Coral
Documentation | Coral
Google Developers Blog: Coral moves out of beta
Google Developers Blog: Coral moves out of beta
Get started with the USB Accelerator | Coral
USB Accelerator | Coral

Google Just Turned the Raspberry Pi into a Supercomputer... - YouTube
Edge TPU live demo: Coral Dev Board & Microcontrollers (TF Dev Summit '19) - YouTube

Intel

Intel Loihi: neuromorphic processor
Brains scale better than CPUs. So Intel is building brains – Ars Technica

OpenVINO™ Toolkit Documentation - OpenVINO™ Toolkit
Enabling Real-Time Face Expression Classification using Intel®...
Neural Style Transfer with OpenVINO™ Toolkit - Intel Software Innovators - Medium

Microcontrollers

TensorFlow Lite for Microcontrollers
AI on a microcontroller with TensorFlow Lite and SparkFun Edge
TinyML is giving hardware new life – TechCrunch

SparkFun Edge Development Board - Apollo3 Blue - DEV-15170 - SparkFun Electronics
Adafruit EdgeBadge - TensorFlow Lite for Microcontrollers ID: 4400 - $35.95 : Adafruit Industries, Unique & fun DIY electronics and kits
ESP-EYE Overview | Espressif Systems

Inference Server

Cortex

Deploy machine learning models in production - Cortex
cortexlabs/cortex: Cloud native model serving infrastructure
Why we’re writing machine learning infrastructure in Go, not Python

NVIDIA TensorRT Inference Server

NVIDIA TensorRT Inference Server Boosts Deep Learning Inference | NVIDIA Developer Blog introductory blog post
NVIDIA TensorRT Inference Server — NVIDIA TensorRT Inference Server documentation
NVIDIA/tensorrt-inference-server: The TensorRT Inference Server provides a cloud inferencing solution optimized for NVIDIA GPUs.

Language Specific

Golang

Google’s Go language ventures into machine learning | InfoWorld

JavaScript

10 Machine Learning Examples in JavaScript - Tutorialzine
JavaScript and machine learning: Google shows what's possible using the web programming language - TechRepublic
AI in browsers: Comparing TensorFlow, ONNX, and WebDNN for image classification - LogRocket Blog
4 reasons to learn machine learning with JavaScript | VentureBeat

aijs.rocks

ml5js·Friendly Machine Learning For The Web

A Neural Network Playground

deeplearn.js
Neural Networks in JavaScript with deeplearn.js - RWieruch

brain.js

Synaptic - The javascript neural network library

Python

data-analytics-python

Why you should use Python for machine learning | InfoWorld
5 Python distributions for mastering machine learning | InfoWorld

scikit-learn: machine learning in Python non neural
Basic Machine Learning with SciKit-Learn | Graham Wheeler's Random Forest
Easily visualize Scikit-learn models’ decision boundaries

Scikit-learn is a free software machine learning tool for the Python programming language. It features various classification, regression, and clustering algorithms with support vector machines. Simple and efficient tools for predictive data analysis. Accessible to everybody and reusable in many contexts. Scikit-learn is one of the best Python tools to learn in 2022.

Welcome to Spinning Up in Deep RL! — Spinning Up documentation
Spinning Up in Deep RL

Java

Deeplearning4j: Open-source, Distributed Deep Learning for the JVM

C sharp

Infer.NET
The Microsoft Infer.NET machine learning framework goes open source - Microsoft Research

Pokedex with AI

Using TensorFlow Lite and ML Kit to Build a “Pokédex” in Android | by Harshit Dwivedi | Heartbeat
the-dagger/Pokidex: Android app that identifies and detects Pokemons in the provided Image using Tensorflow Lite and Firebase MLKit

Classifying Pokémon Images with Machine Learning | CodeAI

Dataset

Pokemon Image Dataset | Kaggle
How to create a deep learning dataset using Google Images - PyImageSearch
How to (quickly) barto
uild a deep learning image dataset - PyImageSearch
Image hashing with OpenCV and Python - PyImageSearch
Pokemon Generation One | Kaggle

Artificial Intelligence

AI vs Machine Learning

Video

Courses

MLOps

Ethics

Limits/Is AI intelligent?

Singularity

Symbolic AI

AI winter

GoodAI

Performance/Accuracy

Version Control

#perfmatters

Model Repository

AI quirks (adversarial examples)

Natural Language

Stemming

STT

TTS

Chatbot

Voice Isolation

Computer Vision

Image Pre processing

Clustering

categorical variables

Forecasting

DuHL

Decision Tree

Random Forest

SVM

AutoML

Deep Image

Scoring

Recommendation System

Unsupervised/Weakly Supervised Learning

Reinforcement Learning

Genetic Algorithm

DeepMind

Evolutionary Algorithm

Bayesian learning

Playing Games

UnityML

Mario

Project Malmo

Deep Learning

History

Analog ANN

Math

Medical

Transfer Learning

CNN

RNN

Explainable AI

Coding Deep Learning for Beginners

Generative Network

Survival Analysis

DL Frameworks

Pipeline

Comparison

CNTK

ONNX

TensorFlow

Ecosystem

TensorFlow Runtime (TFRT)

PyTorch

Ecosystem

MXNet

Theano

DSSTNE

Caffe

AI Model Security

Edge AI

NVIDIA TensorRT

TensorFlow lite

Google AIY

Federated Learning

Coral USB Accelerator/TPU

Intel

Microcontrollers