Deep Learning

neural style transfer using tensorflow 2

When the style of one image is mixed with content of another image then it is called Style Transfer and we are using a neural network to do so call Neural Style Transfer. As we are dealing with images so we need a convolutional neural network. Neural Style Transfer was first published in the paper “A Neural Algorithm of Artistic Style” by Gatys et al., originally released in 2015 and in this session, we are implementing this paper using Tensorflow 2.0.

By Tarun Bisht on March 11, 2020

Deep Learning

building intuition for recurrent neural network

So one of the most difficult topics to understand is Recurrent Neural networks and LSTMs. When I jumped from traditional neural networks to recurrent neural networks to recurrent networks for the first time I could not build intuition about it. Scraping internet finding blog posts and videos reading as much I can and do not get inside feeling that I got it Ya!. Then I tried to follow Richard Feynman’s approach of learning to learn it and this blog post is the result of it. As I was reviewing my notes I found this topic and I thought the better place for this is in a blog instead of my rough and bad writing and decided to make it live.

By Tarun Bisht on September 17, 2019