A Better Visualization of L1 and L2 Regularization
by likkhian on 05 March 2020
Here's an intuitive explanation of why L1 regularization shrinks weights to 0. Regularization...
Modeling and Output Layers in BiDAF — an Illustrated Guide with Minions
by basil.han on 13 December 2019
BiDAF is a popular machine learning model for Question and Answering tasks. This article explain...
AI and Curve Fitting
by basil.han on 25 November 2019
This article from last year popped up in my newsfeed recently. It contains a discussion on wheth...
Attention Mechanism in Seq2Seq and BiDAF — an Illustrated Guide
by basil.han on 20 November 2019
Sequence-to-sequence (seq2seq) and Bi-Directional Attention Flow (BiDAF) are influential NL...
Demystifying RPA
by Thu Ya Kyaw on 15 October 2019
What is RPA? The buzzword “RPA” has been gaining traction in recent years across different in...
Word Embedding, Character Embedding and Contextual Embedding in BiDAF — an Illustrated Guide
by basil.han on 08 October 2019
BiDAF is a popular machine learning model for Question and Answering tasks. This article il...
An Illustrated Guide to Bi-Directional Attention Flow (BiDAF)
by basil.han on 01 October 2019
This article illustrates the workings of BiDAF, an NLP model that has pushed the envelope in the...
Illustrated: 10 CNN Architectures
by raimibinkarim on 26 September 2019
A compiled visualisation of the common convolutional neural networks.
Animated RNN, LSTM & GRU
by raimibinkarim on 19 June 2019
Recurrent neural networks are a class of artificial neural networks which are often used with se...
10 Gradient Descent Optimisation Algorithms + Cheat Sheet
by raimibinkarim on 19 June 2019
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.
Text-based Graph Convolutional Network — Bible Book Classification
by weetee on 21 May 2019
A semi-supervised graph-based approach for text classification and inference The most beauti...
Simple Neural Network Model Using TensorFlow Eager Execution
by yxlee245 on 12 May 2019
The Eager way to building deep learning models
From-scratch implementation of AlphaZero for Connect4
by weetee on 29 April 2019
Step-by-step illustration on how one can implement AlphaZero on games using just PyTorch and sta...
Intuitions on L1 and L2 Regularisation
by raimibinkarim on 24 April 2019
Explaining how L1 and L2 work using gradient descent