Some of my tutorials
- A brief overview of proximal algorithms
- A simple derivation of the backpropagation (backprop) algorithm for training artificial neural networks in matrix form can be found here.
- For a brief tutorial on gradient backpropagation through a long short-term memory (LSTM) cell, see this.
- A simple demo of Sparse Land, including, various sparse signal recovery (compressed sensing) algorithms, demonstration of simple dimensionality reduction schemes based on Discrete Cosine Transform (DCT) and Principal Component Analysis (PCA), and so on.
Some interesting resources on deep learning and neural networks
- Machine learning, deep learning, and artificial intelligence easy-to-digest cheatsheets
- A very nice browser-based platform for training and visualizing deep networks
- A neural network playground!
- Visualizing and understanding what different layers in a CNN are learning!
- A very nice and well-explained tutorial on Variational Auto-encoders (VAEs)! + Take also a look at this one
- Machine Learning Notebooks
- Blog posts on deep generative models
- Convolution Visualizer
Miscellaneous interesting articles across the web
- Bayesian inference for hiring!
- A very nice comparison of frequentist and Bayesian inference + Explaining it via a fictional dialogue
- A great blog post that explains backpropagation through computational graphs in a very simple way!
- For an introduction to the calculus of variations, see this nice post and the references therein
- A nice book to learn Python for data science + Check this post + CS231 course
- Computational Statistics in Python
- Approximate inference in Bayesian Learning
- Derivations for Linear Algebra and Optimization
- A nice blog post on Markov Chain Monte Carlo techniques
- An interesting and well-written overview paper about non-convex optimization for low-rank matrix factorization: Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
- A very nice document on optimization for machine learning
Different strategies for approximating intractable normalizing constants, and KL divergence between a Gaussian and a non-Gaussian distribution
- Gaussian Kullback-Leibler Approximate Inference
- Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models
- Non-Gaussian likelihoods for Gaussian Processes
- Approximating the KL divergence between two densities using gamma-divergence
Some useful books
- Information Theory, Inference and Learning Algorithms (by D. MacKay)
- Introduction to Applied Linear Algebra (by S. Boyd and L. Vandenberghe)
- The Matrix Cookbook (a must-have handbook!)