deep Sparse Rectifier Neural Networks

Introduction

Two trends in Deep Learning can be seen in terms of architecture improvements. The first is increasing sparsity (for example, see convolutional neural nets) and increasing biological plausibility (biologically plausible sigmoid neurons performing better than tanh neurons). Rectified linear neurons are good for sparsity and for biological plausibility, thus should increase performance.

Experiments

Networks with rectifier neurons were applied to the domains of image recognition (both black and white, colour and stereo images) and sentiment analysis.

Results

In the NORB and sentiment analysis cases, the network benefited greatly from pre-training. However, the benefit in NORB diminished as the training set size grew.

Criticism

Rectifier neurons really aren't biologically plausible for a variety of reasons. Namely, the neurons in the cortex do not have tuning curves resembling the rectifier. Additionally, the ideal sparsity of the rectifier networks were from 50 to 80%, while the brain is estimated to have a sparsity of around 95 to 99%.