Attention mechanisms in neural networks

DATE AND LOCATION CHANGED: MEETING WEDNESDAY APRIL 25th AT MOONLIGHTER

Many recent neural network architectures use some form of "attention", which allows the network to identify import regions of its input and summarize them apart from other irrelevant data. Examples of this might be visual attention to identify the location of objects in an image or attention over words in a sentence for language-to-language translation. This meetup will discuss a few of the more commonly used formulations of attention.

If you're not familiar with neural attention models, try to read one (or more) of these articles before the meetup:

* Attention in Neural Networks and How to Use It (http://akosiorek.github.io/ml/2017/10/14/visual-attention.html)
* Attention and Augmented Recurrent Neural Networks (https://distill.pub/2016/augmented-rnns/)
* The Transformer - Attention is all you need (https://mchromiak.github.io/articles/2017/Sep/12/Transformer-Attention-is-all-you-need/)

Location: Moonlighter Maker Space (2041 NW 1st Place Miami, FL 33127)