Jack Dermody


Sentiment Analysis

Otherwise, these layers would continue to learn from the backpropagation signals from the fourth classifier and we wouldn't know where the gain is.

Teaching a Recurrent Neural Net Binary Addition

The network is trained using backpropagation through time and with a batch size of 16 and learning rate of 0.01. During backpropagation this all happens in reverse, however the supplied memory is only updated when backpropagating (through time) the first item in the sequence.

Convolutional Neural Networks

The CNN learns to improve each of the filter weights by backpropagation.