Presentation on Capsule Networks - Deep Learning Study Group - Raleigh

2018-04-15
Organizer: Deep Learning RTP
Click here for registration info

Clark Huang will be giving a presentation on Capsule Networks. Here is Geoffrey Hinton's Paper introducing Capsule Networks to the world
https://papers.nips.cc/paper/6975-dynamic-routing-between-capsules.pdf

Bring a laptop and let's study together.

First timer? Here's some background (http://www.fast.ai/2017/11/16/what-you-need/)

A good place to start is Practical Deep Learning For Coders (http://course.fast.ai/) from fast.ai. Learn how to build state of the art models without needing graduate-level math—but also without dumbing anything down. It's totally free! (but you might end up paying AWS or Paperspace about $20 to use their GPU servers)

They say the best way to learn is to teach. So come on down to ask and answer questions about the notebooks you're working through.

Everyone is welcome (http://www.fast.ai/about/).

This 7-week course is designed for anyone with coding experience, and some memory of high-school math. You will start with step one—learning how to get a GPU server online suitable for deep learning—and go all the way through to creating state of the art, highly practical, models for computer vision, natural language processing, and recommendation systems. There are around 20 hours of lessons, and you should plan to spend around 10 hours a week for 7 weeks to complete the material.

----

Poster: triangletech