Profile cover photo
Profile photo
Martin Heusel
56 followers
56 followers
About
Martin's posts

Post has shared content
In 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. 

Post has shared content
Deep learning has shown remarkable success on some of the world’s most difficult computer science challenges. Today on the Google Research blog we go into how Long Short-term Memory Recurrent Neural Networks (LSTM RNNs) are being used to improve Google Voice transcription. 

Post has attachment

Post has shared content

Post has shared content

Post has shared content
New kernel release announcement, made from 30k feet, with Walter the Labradoodle sitting in the seat next to me and then falling asleep on my arm. (https://instagram.com/walterthelabradoodle/ )

3.10.81
3.14.45
4.0.6

Also, now that 4.1 is out, time to announce that it will be the next "Long Term Support" kernel I'll be maintaining for the next two years.
Photo
Photo
6/22/15
2 Photos - View album

Post has attachment

Post has attachment

Post has shared content
The journal Nature just published a review paper on deep learning co-authored by myself, Yoshua Bengio​, and Geoff Hinton.

It is part of a "Nature Insight" supplement on Machine Intelligence, with two other articles on machine learning by Zoubin Ghahramani​ (probabilistic machines) and Michael Littman​ (reinforcement learning).

Paper: http://www.nature.com/nature/journal/v521/n7553/full/nature14539.html

Insight supplement on AI: http://www.nature.com/nature/journal/v521/n7553/index.html#insight

Post has attachment
Park Racer
Photo
Wait while more posts are being loaded