Introduction

A novel regularization is proposed that enforces the output of a model to be isotropically smooth around each input data point irrespective of the availability of the training label. This is achieved by investigating the local anisotropy around each input data point and smoothing the model in the most anisotropic direction.

Method

The approach to investigate the local anisotropy around each data point is to find the direction of a small perturbation that the model is most sensitive to. The sensitivity of the model is measured in terms of the KL divergence between the output class probability distribution given the input and the input plus the perturbation. The desired perturbation is called the 'virtual adversarial perturbation'. The model is supposed to minimize the supervised loss (cross entropy, MSE etc) as well as the sensitivity to the virtual adversarial perturbation.

Intuition

One way to think about why this works is that VAT pu...

Prerequisites: Standard Convolutional Neural Networks (CNNs). For Neural Machine Translation background read this reply to this post.

Motivation 1: Why character by character?

• Robust to handling spelling mistakes, typos.
• Handling long words that have sub-structure.

Motivation 2: Why multi-lingual? (one model for multiple languages)

• Language switching! i.e. using an English phrase in the middle of a French sentence (real-world scenario)
• Reduce over-fitting (when languages have similar characteristics)

Challenge = Computation

Computation is quadratic in length of source sentenc...

Training an LSTM (NTM—Neural Turing Machine—is tested too) to output an update for a steepest descent iteration at each time step. Aptly titled “Learning to learn by gradient descent by gradient descent”.

Anybody interested in trying Learning to learn to learn by gradient descent by gradient descent by gradient descent?

A clockwork RNN is a recurrent neural network (RNN) architecture designed to remember things easily over long periods of time. It is a follow up on Long Short-Term Memory architecture (also by Jurgen Schmidhuber). 

In my opinion, the paper is quite interesting and deserves more attention than it has received.