Clearest explanations of difficult concepts known to me
- Decision Trees. A visual Introduction to Machine Learning by R2D3 (Stephanie Yee and Tony Chu)
- AutoRegressive Integrated Moving Average. Chapter 8: ARIMA models of Forecasting: Principles and Practice by Rob J Hyndman and George Athanasopoulos of Monash University, Australia
- Stacking, diagram by Faron on kaggle forums.
- Matrix calculus on Wikipedia
- Matrix Decompositions Cheat Sheet by Maxim Rakhuba and Alexandr Katrutsa for Skoltech
- Principal Component Analysis versus Multidimensional Scaling by Théo Lacombe for École polytechnique
-
Universal approximation theorem. A visual proof that neural nets can compute any function by Michael Nielsen
-
All neural networks ever. The Neural Network Zoo by Fjodor van Veen for The Asimov Institute
-
Recurrent Neural Networks. The Unreasonable Effectiveness of Recurrent Neural Networks by Andrej Karpathy
-
Long Short Term Memory. Understanding LSTM Networks by Christopher Olah
-
TorchText. Pytorch sentiment analysis by Ben Trevett
-
Various optimizers. An overview of gradient descent optimization algorithms by Sebastian Ruder
-
Nesterov momentum. Momentum in machine learning? What is Nesterov momentum? by Abhinav Mahapatra
Basic course by HSE. Advanced course by DeepPavlov.
- Reinforcement learning algorithms: table 2 (page 2) of OpenSpiel: A Framework for Reinforcement Learning in Games