Paper repro: “Self-Normalizing Neural Networks”

Paper repro: “Self-Normalizing Neural Networks”

  • March 13, 2018
Table of Contents

Paper repro: “Self-Normalizing Neural Networks”

SNNs are really cool: their goal is to create neural networks in which, if the input of any layer is normally distributed, the output will automatically also be normally distributed. This is amazing because normalizing the output of layers is known to be a very efficient way to improve the performance of neural networks, but the current ways to do it (eg BatchNorm) basically involve weird hacks, while in SNN the normalization is an intrinsic part of the mathematics of the neural net.

Source: becominghuman.ai

Tags :
Share :
comments powered by Disqus

Related Posts

Google helps Pentagon analyze military drone footage—employees “outraged”

Google helps Pentagon analyze military drone footage—employees “outraged”

A report from Gizmodo says that Google is partnering with the United States Department of Defense and building drone software. The project will reportedly apply Google’s usual machine learning prowess to identify objects in drone footage. Google’s involvement in the project wasn’t public, but it was apparently discussed internally at Google last week and leaked.

Read More
AI Researchers Aim to Crack Code on ‘Sun Energy’

AI Researchers Aim to Crack Code on ‘Sun Energy’

Since the ’50s, scientists have chased the promise of clean energy from sun-like reactions between deuterium and tritium, the plentiful isotopes of hydrogen. This carbon-free energy, achieved at temperatures of 360 million degrees Fahrenheit, would offer a great way to heat water and, in turn, spin turbines to create countless kilowatts of electricity.

Read More
The Building Blocks of Interpretability

The Building Blocks of Interpretability

Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them — and the rich structure of this combinatorial space.

Read More