Published inTowards Data ScienceHow to use TorchText for neural machine translation, plus hack to make it 5x fasterProcessing text is the first step toward any successful project in NLP, and fortunately the tools to help us here are growing evermore…Sep 27, 20184Sep 27, 20184
Published inTowards Data ScienceHow to code The Transformer in PytorchCould The Transformer be another nail in the coffin for RNNs?Sep 27, 201834Sep 27, 201834
A simple vectorised neural network in Octave in 11 lines of code!It’s hard to believe that only two weeks ago I knew less about neural networks than I did about the inner workings of North Korea.May 19, 20182May 19, 20182
Octave code for Univariate linear regression: my first implementationThis follows my former post on how gradient descent works in linear regression.May 2, 2018May 2, 2018
First weeks of Andrew Ng: Beginner’s steps for gradient descent and the cost function in univariate…The first weeks of Andrew Ng’s machine learning Coursera course can be slightly harrowing for those of us with little experience of…Apr 25, 20182Apr 25, 20182
