Deep Learning Technical Meetup Nov 9 @Datalogue

Dear Deep Learning Montrealists!

We're happy to announce our very first Technical Meetup, to be held November 9th at Datalogue (https://www.datalogue.io/)! This is a new format and we are thinking of focusing on a specific theme, attention mechanisms in this case. We will review attention and state-of-the-art research from the past year. The format will be part presentations, interaction, pizza! Details will follow.

Since space is limited and since the meetup targets an audience knowledgeable in deep learning, please sign up here (https://goo.gl/gqHxn2). You will be registered once you receive a confirmation from an organizer. [UPDATE: registration is closed]

Thank you Datalogue (https://www.datalogue.io/) and Zafarali Ahmed (http://www.zafarali.me/) for helping to organize this!

Zaf and Andre will cover attention mechanisms based on the following papers:

• Neural Machine Translation by Jointly Learning to Align and Translate (https://arxiv.org/abs/1409.0473)

• A Deep Reinforced Model for Abstractive Summarization (https://arxiv.org/abs/1705.04304)

• Get To The Point: Summarization with Pointer-Generator Networks (https://arxiv.org/abs/1704.04368)

• Attention-over-Attention Neural Networks for Reading Comprehension (https://arxiv.org/abs/1607.04423)

• End-To-End Memory Networks (https://arxiv.org/abs/1503.08895)

• Attention Is All You Need (https://arxiv.org/abs/1706.03762). Make sure to checkout the Google Research blog (https://research.googleblog.com/2017/08/transformer-novel-neural-network.html) about this ;)

• Recurrent Models of Visual Attention (https://papers.nips.cc/paper/5542-recurrent-models-of-visual-attention.pdf)