Machine Learning

Tools

• Scikit-multilearn - http://scikit.ml/index.html
• scikit-multiflow: for multi-output/multi-label and stream data.- https://scikit-multiflow.github.io/
• scikit-plot: plot models analysis - https://github.com/reiinakano/scikit-plot
• yellowbrick various model visualizations - https://www.scikit-yb.org/en/latest/
• Scikit-lego: interesting prebuild pipelines and transformers for sklearn - https://scikit-lego.readthedocs.io/en/latest/
• List of various scikits - http://scikits.appspot.com/scikits
• Information Theoretical Estimators (ITE) in Python - https://bitbucket.org/szzoli/ite-in-python/src/master/ Paper
• HYPERBOLIC DEEP LEARNING - A nascent and promising field - http://hyperbolicdeeplearning.com/
• Optimial Transport - https://pythonot.github.io/quickstart.html
• EMLP: Equivariant Representations layers - https://emlp.readthedocs.io/en/latest/index.html
• BOLT: 10x faster matrix and vector operations - https://github.com/dblalock/bolt
• Macarico: learning to search - https://github.com/hal3/macarico
• A Collection of Conference & School Notes in Machine Learning - https://github.com/visual-ml-notes/visual-machine-learning-notes
• Python Toolkit of Statistics for Pairwise Interactions (pyspi) - https://github.com/olivercliff/pyspi
• pulearn: Positive-unlabeled learning with Python - https://pulearn.github.io/pulearn/

ML Engineering

• https://github.com/EthicalML/awesome-production-machine-learning
• Machine Learning Systems Design - https://github.com/chiphuyen/machine-learning-systems-design
• https://www.oreilly.com/radar/what-you-need-to-know-about-product-management-for-ai/
• https://github.com/Intellicode/ml-engineering-resources
• Top 30 ML in Production Resources - https://mlinproduction.com/top-30-ml-in-production-resources-guide/
• 150 Successful Machine Learning Models: 6 Lessons Learned at Booking.com - https://dl.acm.org/doi/pdf/10.1145/3292500.3330744
• Rules of Machine Learning: Best Practices for ML Engineering - http://martin.zinkevich.org/rules_of_ml/rules_of_ml.pdf On google blog
• Troubleshooting Deep Neural Networks: A Field Guide to Fixing Your Model - http://josh-tobin.com/troubleshooting-deep-neural-networks.html
• Lecture 6: MLOps Infrastructure & Tooling - https://fullstackdeeplearning.com/spring2021/lecture-6/
• Made with ML - https://madewithml.com/
• Machine Learning Systems Design - https://stanford-cs329s.github.io/2021/slides/cs329s_12_slides_sara_google.pdf
• Monitering model/data Drift - https://evidentlyai.com/blog/ml-monitoring-do-i-need-data-drift
• Machine Learning in Science and Industry slides - https://arogozhnikov.github.io/2017/04/20/machine-learning-in-science-and-industry.html
• Machine learning in production - https://applyingml.com/papers/
• How to navigate through the ML research information flood - https://drive.google.com/file/d/1zKAKBmOzM8KOnVnO09Xc_4Mne1z4pEUa/view
• SRE for ML: The First 10 Years and the Next 10 - https://www.usenix.org/conference/srecon21/presentation/underwood-sre-ml
• ML Crash Course from Google which included practical aspects of ML - https://developers.google.com/machine-learning/crash-course

Theory

• The Theory Behind Overfitting, Cross Validation, Regularization, Bagging, and Boosting: Tutorial
• Blog: Shape matching with time series data
• Notes on information theory - Information Theory for Intelligent People - Simon DeDeo
• Notes on Bayesian reasoning - Bayesian Reasoning for Intelligent People - Simon DeDeo
• Mathematics of Machine Learning book
• ALGORITHMS FOR DECISION MAKING
• Linear Algebra Done Right - Videos and Slides
• Old and New Matrix Algebra Useful for Statistics
• Linear Algebra by Jim Hefferon
• Intro to linear algebra in Numpy
• DATASET SHIFT IN MACHINE LEARNING
• Probability Divergences and Generative Models Video
• Generalized energy-based models Video
• Kernel Methods
• Non-Euclidean Methods in Machine Learning - “Data has Shape and Shape has Meaning” - Stanford Course
• THE SOCIETY OF MIND by Marvin Minsky MIT Course

Optimization

• Jupyter notebooks on various optimization topics
• Notebook on Optimal transport
• Numerical Tours - Python
• Algebraic and Topological Tools in Linear Optimization
• Algebraic, Geometric, and Topological Methods in Optimization
• MOSEC Cookbook on Convex Optimization - Handy cheatsheet
• Energy Based Machine Learning video tutorial from IBM research
• Google OR Tools for Operations Research optimization problems
• Computational Control Theory - Princton course
• Proximal Operators implementations
• CMU series of tutorials for conducting computational experiments with optimization solvers
• Computational Optimal Transport

Structured prediction

• Course: https://taehwanptl.github.io/
• CVPR 2011 Tutorial - Structured Prediction and Learning in Computer Vision: http://www.nowozin.net/sebastian/cvpr2011tutorial/
• Pytorch Struct - http://nlp.seas.harvard.edu/pytorch-struct/README.html

Graphical models and variational inference

• Graphical Models, Exponential Families, and Variational Inference: https://people.eecs.berkeley.edu/~wainwrig/Papers/WaiJor08_FTML.pdf
• Probabilistic Graphical Models stanford course: https://cs228.stanford.edu/ [Course notes]
• Differential Inference: A Criminally Underused Tool - https://github.com/srush/ProbTalk/blob/main/talk.notebook.ipynb
• Probabilistic Machine Learning: Advanced Topics - https://probml.github.io/pml-book/book2.html

Extreme classification

• Slide deck from above course

Online learning

• Online Learning, Interactive Machine Learning, and Learning from Human Feedback
• Lecture notes on Online Learning
• Machine Learning for Data Streams using MOA
• Introduction to Online Convex Optimization - Website
• Prediction, Learning, and Games
• Online learning, boosting and Games - Prof. Yoav Freund
• Python implementation of concept-drift algorithms for Online Learning
• ICML 2020 TUTORIAL ON PARAMETER-FREE ONLINE OPTIMIZATION
• A Modern Introduction to Online Learning

Positive Unlabelled (PU) learning

• An introductory tutorial to the "Learning from Positive and Unlabeled Data" field videos
• PU Learning - Learning from Positive and Unlabeled Examples - UIC Resources

Concept Drift

• Handling Concept Drift
• Learning under Concept Drift

Domain Adaptation

• Office-Home Dataset - http://hemanthdv.org/OfficeHome-Dataset/
• ImageClef - https://www.imageclef.org/2014/adaptation
• Pg. 13 of this paper suggests data for open world/domain adaptation - https://arxiv.org/pdf/2004.07780.pdf

Bandit Algorithms

• A blog and book on bandit algorithms by Tor Lattimore and Csaba Szepesvari
• I'm a bandit - Random topics in optimization, probability, and statistics. By Sébastien Bubeck
• A tutorial on Thompson Sampling

Continual learning

• Meta-Learning Representations for Continual Learning - https://github.com/khurramjaved96/mrcl
• Distillation and Incremental Classifier Learning - https://github.com/khurramjaved96/incremental-learning
• Awesome Continual Learning - https://github.com/khurramjaved96/awesome-continual-learning
• Continual Unsupervised Representation Learning - https://arxiv.org/abs/1910.14481
• Continual Learning Papers Library by ContinualAI - https://www.zotero.org/groups/2623909/continual_learning_papers/library
• Sequoia A Playground for research at the intersection of Continual, Reinforcement, and Self-Supervised Learning. - https://github.com/lebrice/Sequoia
• Continual Learning: Towards “Broad” AI Winter 2021, A Course offered by the Université de Montréal - https://sites.google.com/view/ift6760-b2021/schedule?authuser=0
• A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning - Martin Mundt - https://drive.google.com/file/d/1fDOwLI3_EXxeEZyRCbGXFPSv2i39Tf_A/view
• Tutorial 2: Out-of-distribution (OOD) Learning Week 3, Day 4: Continual Learning
• CVPR21 Continual Learning Challenge - https://eval.ai/web/challenges/challenge-page/829/overview
• Avalanche: an End-to-End Library for Continual Learning - https://avalanche.continualai.org/

Multi task learning

• CS 330: Deep Multi-Task and Meta Learning - http://cs330.stanford.edu/

Learning to Rank

• Tutorial using TF-Rank

Neural Ordinary Differential Equations

• https://github.com/msurtsukov/neural-ode
• https://jontysinai.github.io/jekyll/update/2019/01/18/understanding-neural-odes.html
• Augumented Neural ODE: https://arxiv.org/abs/1904.01681

Active learning

• Importance weighted active learning for streams: http://www.yisongyue.com/courses/cs159/lectures/active_learning.pdf
• Summary of active learning: http://www.yisongyue.com/courses/cs159/lectures/active_notes.pdf
• Good survey of potential issues with active learning: http://proceedings.mlr.press/v16/settles11a.html
• Human-in-the-Loop Machine Learning by Robert Munro - Active learning in pytorch from book Cheatsheat on active learning
• DUALIST: Utility for Active Learning with Instances and Semantic Terms - https://github.com/burrsettles/dualist/blob/master/README.md

Multiple instance learning

• Good survey: https://arxiv.org/abs/1612.03365

Self-supervised learning

• Slides by Andrew Zisserman (DeepMind) with focus on Images and Videos: https://project.inria.fr/paiss/files/2018/07/zisserman-self-supervised.pdf

Reinforcement learning

• Course on Online Learning, Bandits, Reinforcement and Imitation Learning: https://sites.google.com/view/cs-159-spring-2018/home
• Python code examples for the book: https://github.com/ShangtongZhang/reinforcement-learning-an-introduction
• Approximate Dynamic Programming
• Multiagent Systems - Algorithmic, Game-Theoretic, and Logical Foundations
• Book on Distributional Reinforcement Learning

Transfer Learning

• Good overview of all types of transfer learning approaches (in Chinese): https://github.com/jindongwang/transferlearning

Multimodal learning

• Multimodal Machine Learning: A Survey and Taxonomy - https://arxiv.org/abs/1705.09406

Applications

• List of applications across various industries - https://github.com/firmai/industry-machine-learning#legal
• Visual explanations of ML algorithms - http://visxai.io/2018.html
• Javascript animated examples from Artificial Intelligence - A Modern Approach by Stuart Russell and Peter Norvig: http://aimacode.github.io/aima-javascript/
• Adaptive Language Models in JavaScript - https://github.com/google-research/google-research/tree/master/jslm

Interpretability

• ML Interpratation in python - https://github.com/jphall663/interpretable_machine_learning_with_python
• Explanatory Model Analysis - https://github.com/pbiecek/ema
• Interesting resources related to XAI (Explainable Artificial Intelligence) - https://github.com/pbiecek/xai_resources

Control Theory

• Engineering Media: Control theory posts, lectures, and book - https://engineeringmedia.com/
• Resourcium - https://resourcium.org/

Graph Neural Networks

• A Complete Beginner's Guide to G-Invariant Neural Networks - https://invariances.org/ginvariance-tutorial/
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges - https://geometricdeeplearning.com/lectures/
• Non-Euclidean Methods in Machine Learning - http://graphics.stanford.edu/courses/cs468-20-fall/schedule.html
• Introduction to Graph Neural Nets with JAX/jraph - https://github.com/deepmind/educational/tree/master/colabs/summer_schools