Feedforward Networks

Highway Network

Introduced by Srivastava et al. in Highway Networks

A Highway Network is an architecture designed to ease gradient-based training of very deep networks. They allow unimpeded information flow across several layers on "information highways". The architecture is characterized by the use of gating units which learn to regulate the flow of information through a network. Highway networks with hundreds of layers can be trained directly using stochastic gradient descent and with a variety of activation functions.

Source: Highway Networks


Paper Code Results Date Stars


Task Papers Share
Speech Synthesis 41 33.88%
Text-To-Speech Synthesis 15 12.40%
Speech Recognition 6 4.96%
Language Modelling 6 4.96%
Voice Cloning 5 4.13%
Voice Conversion 4 3.31%
Expressive Speech Synthesis 3 2.48%
Test 3 2.48%
Image Classification 2 1.65%