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.

Criticism

Rectified linear neurons really aren't biologically plausible for a variety of reasons. However, they can be transformed into spiking neural networks.