Easy to use recipes in diverse domains using diverse frameworks.

Torch speech generator

Text generator using Torch

Adding attention

Attention using TensorFlow.

Batch normalization

A way to use less epochs, less sensitive to initialization and make regularization obsolete sometimes.

Convolutional autoencoder

2D convolution autoencoder for house numbers.

2D Convolution

Adding convolution to the MNIST classification.

Pooling

Adding pooling layers.

1D Convolution

1D CNN on text towards classification of reviews.

Generalization through regularization

Making a model more generic (less training data dependent) through regularization.

Experimenting with optimizers

On the effect optimizers have on the accuracy.

Hidden layers and units

[crayon-5c98a2de58502236958450/]