# Machine learning

TODO

## Articles

* [You Don’t Need Math For Machine Learning](https://towardsdatascience.com/you-dont-need-math-for-machine-learning-e168b7d973d4)
* [Machine Learning, Kolmogorov Complexity, and Squishy Bunnies](https://theorangeduck.com/page/machine-learning-kolmogorov-complexity-squishy-bunnies)
* [Variational Graph Auto-Encoders](https://arxiv.org/abs/1611.07308)
* [Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations](https://arxiv.org/abs/2110.05960)
* [Evaluating Predictive Distributions: Does Bayesian Deep Learning Work?](https://arxiv.org/abs/2110.04629)
* [Unsolved Problems in ML Safety](https://arxiv.org/abs/2109.13916)
* [Data Movement Is All You Need: A Case Study on Optimizing Transformers](https://arxiv.org/abs/2007.00072)
* [Learning to Superoptimize Real-world Programs](https://arxiv.org/abs/2109.13498)
* [The First Rule of Machine Learning: Start without Machine Learning](https://eugeneyan.com/writing/first-rule-of-ml/)
* [The Values Encoded in Machine Learning Research](https://arxiv.org/abs/2106.15590)
* [Multi-Task Learning as Multi-Objective Optimization](https://arxiv.org/abs/1810.04650)
* [Tutorial: Performance Engineering for Machine Learning and Scientific Computing](https://dblalock.github.io/Performance-Engineering-Tutorial/)
* [A visual introduction to Gaussian Belief Propagation](https://gaussianbp.github.io/)
* [How to avoid machine learning pitfalls: a guide for academic researchers](https://arxiv.org/abs/2108.02497)
* [A Gentle Introduction To Gradient Descent Procedure](https://machinelearningmastery.com/a-gentle-introduction-to-gradient-descent-procedure/)
* [Algorithmic Concept-based Explainable Reasoning](https://arxiv.org/abs/2107.07493)
* [In Search of Lost Domain Generalization](https://arxiv.org/abs/2007.01434)
* [Linear unit-tests for invariance discovery](https://arxiv.org/abs/2102.10867)
* [Solving Machine Learning Performance Anti-Patterns: a Systematic Approach](https://paulbridger.com/posts/nsight-systems-systematic-optimization/)
* [Popular Machine Learning Interview Questions](https://www.thinkdataanalytics.com/machine-learning-interview-questions/)
* [Contrastive Representation Learning](https://lilianweng.github.io/lil-log/2021/05/31/contrastive-representation-learning.html)
* [The Scaling Hypothesis](https://www.gwern.net/Scaling-hypothesis)
* [Towards Causal Representation Learning](https://arxiv.org/abs/2102.11107)
* [An Attention Free Transformer](https://arxiv.org/abs/2105.14103)
* [The Modern Mathematics of Deep Learning](https://arxiv.org/abs/2105.04026)
* [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://arxiv.org/abs/2007.00808)
* [Informative Dropout for Robust Representation Learning: A Shape-bias Perspective](https://arxiv.org/abs/2008.04254)
* [E(n) Equivariant Normalizing Flows](https://arxiv.org/abs/2105.09016)
* [Pay Attention to MLPs](https://arxiv.org/abs/2105.08050)
* [Differentially Private Learning Needs Better Features (or Much More Data)](https://arxiv.org/abs/2011.11660)
* [How to Write Design Docs for Machine Learning Systems](https://eugeneyan.com/writing/ml-design-docs/)
* [The Mathematical Foundations of Machine Learning](https://www.dropbox.com/s/mffzmuo9fvs5j6m/Study_Guide.pdf)
* [Joint Universal Syntactic and Semantic Parsing](https://arxiv.org/abs/2104.05696)
* [GeoGuessing with Deep Learning](https://healeycodes.com/geoguessing-with-deep-learning)
* [Testing ML Systems: Code, Data and Models](https://madewithml.com/courses/mlops/testing/)
* [Free Lunch for Few-shot Learning: Distribution Calibration](https://arxiv.org/abs/2101.06395)
* [An Inferential Perspective on Federated Learning](https://blog.ml.cmu.edu/2021/02/19/an-inferential-perspective-on-federated-learning/)
* [Learning Curve Theory](https://arxiv.org/abs/2102.04074)
* [63 Machine Learning Algorithms — Introduction](https://medium.com/swlh/63-machine-learning-algorithms-introduction-5e8ea4129644)
* [Can a neural network train other networks?](https://towardsdatascience.com/can-a-neural-network-train-other-networks-cf371be516c6)
* [What is concept drift and why is it necessary to detect it?](https://censius.ai/blogs/what-is-concept-drift-and-why-does-it-go-undetected)
* [Understand how data drift affects AI performance and how you can detect them](https://censius.ai/blogs/data-drift-barrier-to-ai-performance)

## Books

* Grokking Machine Learning`[0/350]`
* Grokking Deep Learning`[0/336]`
* [Distributed Machine Learning Patterns](https://www.manning.com/books/distributed-machine-learning-patterns)
* [Practical Deep Learning for Cloud, Mobile, and Edge](https://www.oreilly.com/library/view/practical-deep-learning/9781492034858/)
* [Machine Learning with Python Cookbook](https://www.oreilly.com/library/view/machine-learning-with/9781491989371/)
* Perceptrons: an introduction to computational geometry (Marvin Minsky, Seymour Papert)

## Courses

* [Machine Learning with Python](https://www.freecodecamp.org/learn/machine-learning-with-python/)
* [Full Stack Deep Learning - Spring 2021](https://fullstackdeeplearning.com/spring2021/)
* [Arsenii Ashukha: Ensemble Generation](https://youtu.be/bj933t6rqFw)
* [MLSys Seminars](https://youtube.com/playlist?list=PLSrTvUm384I9PV10koj_cqit9OfbJXEkq)
* [Understanding Deep Learning](https://youtube.com/playlist?list=PLFE-LjWAAP9Q74cGaUF3yqUhqo2kOYY20)
* [How Machine Language Works](https://youtu.be/HWpi9n2H3kE)
* [Optimization Methods for Machine Learning and Engineering (KIT Winter Term 20/21)](https://youtube.com/playlist?list=PLdkTDauaUnQpzuOCZyUUZc0lxf4-PXNR5)
* [Deep Learning на пальцах - 2019](https://youtube.com/playlist?list=PL5FkQ0AF9O_o2Eb5Qn8pwCDg7TniyV1Wb)
* [2020 Machine Learning Roadmap (95% valid for 2022)](https://youtu.be/pHiMN_gy9mk)

## Links

* [Learn Machine Learning](https://machinelearning.to/)
* [Learney](https://app.learney.me/)
* [Machine Learning wiki](https://wiki.kourouklides.com/wiki/Machine_Learning)
* [Deep Learning wiki](https://wiki.kourouklides.com/wiki/Deep_Learning)
* [Дорожная карта математических дисциплин для машинного обучения, часть 1](https://habr.com/ru/post/432670/)
* [Machine Learning Guide (Podcasts)](https://podcasts.apple.com/us/podcast/machine-learning-guide/id1204521130)
* [while True: learn()](https://store.steampowered.com/app/619150/while_True_learn/)
* [Learn Machine Learning in 3 Months](https://github.com/llSourcell/Learn_Machine_Learning_in_3_Months)
* [Awesome Machine Learning and AI Courses](https://github.com/luspr/awesome-ml-courses)
* [Machine Learning Engineer Roadmap in 2021](https://github.com/chris-chris/ml-engineer-roadmap)
* [Machine Learning Roadmap](https://github.com/mrdbourke/machine-learning-roadmap)
* [Best-of Machine Learning with Python](https://github.com/ml-tooling/best-of-ml-python)
* [Machine Learning Collection](https://github.com/aladdinpersson/Machine-Learning-Collection)
* [Awesome Normalizing Flows](https://github.com/janosh/awesome-normalizing-flows)
* [ML YouTube Courses](https://github.com/dair-ai/ML-YouTube-Courses)
* [Machine Learning for Beginners - A Curriculum](https://github.com/microsoft/ML-For-Beginners)
* [MLOps-Basics](https://github.com/graviraja/MLOps-Basics)
* [The Ultimate FREE Machine Learning Study Plan](https://github.com/python-engineer/ml-study-plan)
* [Machine Learning Street Talk](https://www.youtube.com/c/MachineLearningStreetTalk/videos)
* [A Curated list of tools for MLOps](https://censius.ai/mlops-tools)
* [Explaination of common MLOps terms](https://censius.ai/wiki)