What we're about

Are you a busy professional that simply doesn't have time to keep up with all the advances in deep learning? Or unsure of which areas to focus on in the deep learning landscape?

Perhaps you've tried reading some of the more recent Deep Learning papers and implementing online code only to find yourself staring at a screen for hours.

Then this is the place for you, welcome to the group!
We're excited to bring you the latest and greatest in Deep Learning.

What is Deep Learning Dojo?

Deep Learning Dojo V2 (start January 2019) is a limited-run educational meetup that teaches advanced deep learning skills to data science and machine learning practitioners.

What do we do?

Our sessions are in-person lectures that focus on recent advances in the field by presenting them in a digestible way. Our goal is to present the intuition behind the ideas simply and provide you with starter code for your deep learning projects.

This seems really advanced is it worth attending?

If you are interested in deep learning then this absolutely the place for you!
While you may not understand everything our lectures will at the very least help you contextualize the importance of the ideas.

Upcoming events (2)

Introduction to Generative Adversarial Networks (GANs)

Talk: Generative Adversarial Networks (GANs) are a Deep Learning framework where two neural networks compete against each other in a generative game similar to cops and robbers. This method, introduced by Goodfellow in 2014, has gained popularity as an effective way to generate complex visual, auditory, and written content. We will explore the basic concepts, use cases, and code behind GANs. Agenda: 1. Intro and Welcome (5 minutes) 2. Talk (~1 hour) 3. Questions (5 minutes)

Deep Learning on Graph Networks

Needs a location

At this meetup we will host a talk on graph networks in deep learning. Graph networks play a central role for making recommendations in social and professional networks, understanding disease markers in biological pathways and structuring knowledge relations. With Thomas Kipf 2016 popularization of graph convolutional networks traditional methods in deep learning are being applied to graph structures. The result, is a richer set of tools to understand graph networks in machine learning. In this talk we will be focus on basic concepts, use cases as well as providing some starter code. Graph embedding, graph neural networks and some of the recent advances/applications of these networks will be discussed throughout. Tentative schedule: - Introduction (5 min) - Talk (~1 hr) - Questions (5 min) - Mingling (10 min)

Photos (2)