Post

Google+ post
Tim HuttonTim Hutton - 2015-08-27 18:28:49+0000 - Updated: 2015-08-27 18:28:49+0000
Originally shared by Google AIIn the last few years, there have been incredible success applying Recurrent Neural Networks (RNNs) to a variety of problems, such as speech recognition, language modeling, translation, image captioning and more. 

Essential to these successes is the use of a very special kind of recurrent neural network architecture called Long Short Term Memory (LSTM), which accounts for long-term dependencies and relationships in data in order to produce amazing results. 

But what are LTSMs, and how do they work? In a blog post, linked below, Google intern +Christopher Olah gives an overview of LSTMs, explaining why and how they work so well. 

Understanding LSTM Networks -- colah's blog

Shared with: Public
Reshared by: William Rutiser

This post was originally on Google+