Here's an intuitive explanation of why L1 regularization shrinks weights to 0. Regularization...

BiDAF is a popular machine learning model for Question and Answering tasks. This article explain...

This article from last year popped up in my newsfeed recently. It contains a discussion on wheth...

Sequence-to-sequence (seq2seq) and Bi-Directional Attention Flow (BiDAF) are influential NL...

What is RPA? The buzzword “RPA” has been gaining traction in recent years across different in...

BiDAF is a popular machine learning model for Question and Answering tasks. This article il...

This article illustrates the workings of BiDAF, an NLP model that has pushed the envelope in the...

A compiled visualisation of the common convolutional neural networks.

Recurrent neural networks are a class of artificial neural networks which are often used with se...

Gradient descent is an optimisation method for finding the minimum of a function. It is commonly used in deep learning models to update the weights of the neural network through backpropagation. In this post, I will summarise the common gradient descent optimisation algorithms used in popular deep learning frameworks (e.g. TensorFlow, Keras, PyTorch, Caffe). The purpose of this post is to make it easy to read and digest (using consistent nomenclature) since there aren’t many of such summaries out there, and as a cheat sheet if you want to implement them from scratch.

A semi-supervised graph-based approach for text classification and inference The most beauti...

The Eager way to building deep learning models

Step-by-step illustration on how one can implement AlphaZero on games using just PyTorch and sta...

Explaining how L1 and L2 work using gradient descent