Machine Learning Resources

Collection of links, tutorials and courses related to machine learning for easy reference.

Activation Functions

• Understanding Activation Functions in Neural Networks
• Activation Functions in Neural Networks (Sigmoid, tanh, Softmax, ReLU, Leaky ReLU)
• The Challenge of Vanishing/Exploding Gradients
• The Vanishing Gradient Problem
• Mish: Self Regularized Non-Monotonic Activation Function

---

Weight Initialization

• Weight Initialization Techniques in Neural Networks (Zero, Random - He, Xavier)

---

Optimizers

• Understanding All Optimizers In Deep Learning

---

Loss Functions

• Understanding Categorical Cross-Entropy Loss, Binary Cross-Entropy Loss, Softmax Loss, Logistic Loss, Focal Loss and all those confusing names

---

Algorithms

• Naive Bayes Classifier
• Support Vector Machine (SVM) Basic Intuition - Video

---

Regularization

• L1 and L2 Regularization Methods
• Intuitions on L1 and L2 Regularisation
• Elastic Net Regression - Video

---

Dimensionality Reduction

• Multi-Dimension Scaling (MDS)
• Principal Component Analysis (PCA) - Video
• Principal Component Analysis - Explained Visually
• A One-Stop Shop for Principal Component Analysis
• StatQuest: t-SNE, Clearly Explained - Video
• How to Use t-SNE Effectively
• Understanding UMAP

---

Boosting Algorithms

• AdaBoost Tutorial
• AdaBoost Classifier in Python
• Gradient Boosting from scratch
• Basic Ensemble Learning (Random Forest, AdaBoost, Gradient Boosting)- Step by Step Explained
• CatBoost overview
• What is XGBoost
• What is LightGBM, How to implement it? How to fine tune the parameters?

---

Bayesian Networks

• Making Your Neural Network Say “I Don’t Know” — Bayesian NNs using Pyro and PyTorch
• Bayesian deep learning with Fastai : how not to be uncertain about your uncertainty !
• Bayesian Methods for Machine Learning - Coursera

---

Active Learning

• Active Learning: Curious AI Algorithms
• modAL - Active Learning Framework

---

Meta-Learning

• Learning to learn aka Meta-Learning - Curriculum
• MAML tensorflow implementation - Colab Notebook
• Model Agnostic Meta Learning - Video
• Explanation of One-shot Learning with Memory-Augmented Neural Networks

---

CNN

• CS231n: Deep Learning for Computer Vision

---

NLP

• An Intuitive Understanding of Word Embeddings: From Count Vectors to Word2Vec
• Paper Dissected: “Attention is All You Need” Explained
• The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning)
• Transformer Neural Networks - EXPLAINED! (Attention is all you need) - Video
• The Illustrated Transformer

---

Normalization

• Box-Cox Transformations
• The Box-Cox Transformation

---

Instance Segmentation

• Mask Region based Convolution Neural Networks - EXPLAINED! - Video

---

Object Detection

• Region of interest pooling explained
• ROI pooling vs. ROI align
• Region Proposal Network (RPN)

---

GAN

• Generative Adversarial Networks - Video Playlist
• Deep Generative Modeling | MIT 6.S191

---

Reinforcement Learning

• Lectures from DeepMind research lead David Silver's course on reinforcement learning - Lecture Series
• Implementation of Reinforcement Learning Algorithms - Code, exercises and solutions
• A Free course in Deep Reinforcement Learning from beginner to expert - Video series
• Simple Reinforcement Learning with Tensorflow Part 0: Q-Learning with Tables and Neural Networks

---

Recommender System

• Practical Recommender Systems - Book

Misc

• Jupyter Notebook Extensions
• PYRO - Deep Universal Probabilistic Programming
• Online/Incremental Learning with Keras and Creme
• CS 230 - Deep Learning Cheatsheet
• Stanford Machine Learning Notes
• Pretrained models CNNs
• Papers with Code
• colah's blog
• Distill
• MACHINE LEARNING SUMMER SCHOOL 2019 LONDON - Video lectures and slides