Home page

Deconstructing Deep Learning + ╬┤eviations

Drop me an email | RSS feed link : Click
Format : Date | Title
  TL; DR

Total number of posts : 89

Go To : PAPERS o ARTICLES o BOOKS o SPACE

View My GitHub Profile


Go to index

RNN from scratch

Reading time : ~1 min

by Subhaditya Mukherjee

(WIP Skip for now) NLP time!! Here we will look at an RNN from scratch.

Adapting the code from Python Link

First let us take data. Baby names are easiest to find (lool) so I copied around 800 of them from here. Link

To do anything, we need to first understand what the outcome should be. So this is an RNN. Our objective is to build this along with the forward and backward pass.

Related posts:  FP16  AI Superpowers Kai Fu Lee  Digital Minimalism Cal Newport  More Deep Learning, Less Crying - A guide  Super resolution  Federated Learning  Taking Batchnorm For Granted  A murder mystery and Adversarial attack  Thank you and a rain check  Pruning