puneet2000/in-depth-ml

In depth machine learning resources

In-Depth-ML

This repository contains major Machine learning topics with detailed analysis through major Papers , blogs , links and youtube tutorials

Linear Regression

• Covariance matrix
• Linear Regression In depth
• Multicollinearity Analysis 1
• Multicollinearity Analysis 2
• Residual Analysis
• Cofficient of determination
• Outlier Analysis 1
• Outlier Analysis 1
• Local Outlier factors
• Regression Shrinkage and selection via Lasso
• Elastic Net - Regularisation and variable selection

Logistic Regression

• Logistic Regression Concept
• Logit vs Probit model
• Poisson Model
• Pseudo R2 for logistic Regression

Trees

• Decison Tress intermidiate
• Understanding Random Forests
• Decison tree from Scratch 1
• Decison tree from Scratch 2
• Random Subspace Method

Cross Validation

• CV vs Bootstraping
• Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation
• Andrew Ng's Percentile cv method of cross-validation

Support Vector machines

• SVM's concept
• SMO algorithm
• Simplified SMO by stanford

Perceptron Update

• Perceptron 1
• perceptron 2

Linear Discriminant Analysis

• LDA introduction
• Detailed LDA

Boosting

• Boosting 1
• Boosting 2
• Gradient Boost overview
• Gradient Boost from scratch
• Gradient Boosting Machines
• XgBoost
• XGBoost Supplement
• AdaBoost and the Super Bowl of Classifiers
• Adaboost Wikipedia
• Adaboost Tutorial
• Logit Boosting Algorithm
• MadaBoost Algorithm
• BrownBoost Algorithm
• LPBoost Algorithm

Stack Generalization/Stacking

• Stack Generalization by Wolpert
• When does it work?
• Issues with Stack generalisation
• Stacking from scratch in python
• Non-Negative least square cofficient method for classification

Data Preprocessing

• Missing Values
• Outliners
• Categorial Encoding

Constraint solving

• Constraint Solving

Kaggle Past Competitions with winning Solutions

• Kaggle competitions and solutions 1
• Kaggle competitions and solutions 2

Convolutional Neural Networks

• Intiutve Explanation of CNN
• How is a convolutional neural network able to learn invariant features?
• Max vs average Pooling
• Dropout
• Explaining Xavier Initialisation easily
• Xaviers Initialisation
• Batch Normalizaton
• Understanding the backward pass through Batch Normalization Layer
• Random vs Grid Search
• Random Search For Hyper Parameter Optimisation
• Gradient Descent Optimisation
• Adam Optimisation
• Fractional Pooling
• ReLU's
• Data Augmentation
• CNN in Pytorch
• Resnet
• Principal Compponent Analysis

Sequence Models

• Understanding RNN
• Guide to Recurrent Neural Networks: Understanding the Intuition
• Guide to LSTM’s and GRU’s: A step by step explanation
• Neural Turing machines
• HMM
• The magic of LSTM neural networks
• The fall of RNN / LSTM
• Pixel CNN
• Blind Spot problem in PixelCNN
• Gated Pixel CNN

Transpose Convolution

• An Introduction to different Types of Convolutions in Deep Learning
• Up-sampling with Transposed Convolution
• Demystifying Transpose Convolution
• Deconvolution and Checkerboard Artifacts
• Convolution arithmetic tutorial

Generative Adversial Networks

• GAN — GAN Series (from the beginning to the end)
• What is wrong with the GAN cost function?
• EXPLAINING AND HARNESSING ADVERSARIAL EXAMPLES
• Introduction to GANs, NIPS 2016 | Ian Goodfellow, OpenAI
• Differentiable Inference and Generative Models
• Pytorch CycleGAN
• Various GAN's implemented in torch
• Nash Equilibrium
• InfoGAN
• UnrolledGAN
• GAN NUmerics
• cycleGAN
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Improved Techniques for Training GANs
• Are GANs Created Equal? A Large-Scale Study

Probabilistic Models in Deep Learning

• Probabilistic Graphical Models Tutorial — Part 1
• Probabilistic Graphical Models Tutorial — Part 2
• Bayesian Directed Networks
• Markov Undirected Networks
• Gaussian BN
• Exponential Families
• Exact Inference - Vatiable Elimination
• Graph Models in Nutshell

Restricted Boltzmann Machines

• Introduction
• Very Good Explanation of RBM I
• Very Good Explanation of RBM II
• Orignal Paper
• [Guide to Training RBM's]
• Tensorflow Example

Adversial Examples and Adversial Training

• Adversarial Examples and Adversarial Training
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Regularisation of Neural Networks by Enforcing Lipschitz Continuity
• Adversarial Diversity and Hard Positive Generation
• DeepFool: a simple and accurate method to fool deep neural networks
• Universal adversarial perturbations
• Towards Evaluating the Robustness of Neural Networks

Extras and Interesting

• Machine learning cheat sheet
• Probability cheat sheet
• Regularisation
• error Analysis
• MIT probability course
• MIT Machine learning course
• “Deep learning - Information theory & Maximum likelihood.”
• Exemplar CNNs and Information Maximization
• Dilated Convolutions and Kronecker Factored Convolutions
• Swish Activation Function by Google
• Capsule Networks
• Maximum Likelihood Estimation
• Maximum Aposteriori
• Understanding and Using Principal Component Analysis (PCA)
• How PCA works
• Probabilistic Principal Component Analysis
• The Neural Autoregressive Distribution Estimator
• Deep AutoRegressive Networks
• When Bayes, Ockham, and Shannon come together to define machine learning
• No-Free-Lunch and the Minimum Description Length
• No Free Lunch versus Occam’s Razor in Supervised Learning
• No-Free-Lunch and the Problem Description Length
• Demystifying KL Divergence

Other Tutorials

• CS231n Stanford course
• Machine Learning for beginners
• Mathematics of machine learning
• PyTorch tutorials for deep Learning
• PyTorch