Premium Hands-on Workshop: Generative Adversarial Networks and Beyond

Event Information

Share this event

Date and Time

Refund Policy

Refund Policy

Contact the organizer to request a refund.

Eventbrite's fee is nonrefundable.

Event description
Theory and hands on review of Generative Adversarial Networks, how to code them, while building an application to generate images

About this Event

Workshop Overview

Generative Adversarial Networks have been very popular in recent years for various tasks like image generation and data augmentation. A large number of papers at ICLR 2019 were focused on GANs. With the fast pace of the field, you won't be able to stay up to date with the latest if you don't have the right foundational knowledge of how these networks work under the hood. We are offering this workshop to help you step into the depth of GANs. Are you ready?

In this workshop, you will learn the theory and gather hands on experience in some of the most fundamental concepts and practical tips about GANs.

Important Dates

Please note that this workshop will happen on 3 separate evenings:

August 14, 2019

August 21, 2019

August 28, 2019

Office hours will happen on,

August 20, 2019 (in person and online participants, Group office hour with the TAs)

August 27, 2019 (in person and online participants, Group office hour with the TAs)

Date TBC (Group office hour with the instructor, has to be purchased separately)

"Why should I care about GANs?"

GANs and adversarial ML are widely discussed and increasingly used in AI

GANs are rapidly being applied in many of the cutting edge AI applications

“But I don’t care about generating fake photos!”

Adversarial ML has become an integral part of many of the recent ML algorithms

This workshop goes beyond GANs where you will explore adversarial training and their numerous potential applications

Why you should attend

In this 3-session intensive workshop, we will bring you up to speed with everything needed to build a strong background in GANs. It will be a combination of theory and hands-on applications in PyTorch.

This workshop is built on the instructors extensive experience in academia and industry on related topics.

This workshop is the first in its series and paves the way theoretically and technically for many application specific workshops to follow.

Target Audience

Data Scientists, Machine Learning Engineers, Software Engineers, Students, Other Analytics Roles (data analysts, managers, product owners, etc)

Prerequisites

  • Knowledge of Python
  • Knowledge of Machine Leaning
  • Familiarity with deep learning
  • Familiarity with PyTorch or other deep learning frameworks is a plus
  • This is a beginner to intermediate workshop

Learning Outcomes

We will build a working application in Python using GANs and image processing to generate and translate images

  • Understand how a vanilla GAN works
  • Understand how and image to image translation GAN works
  • Be able to explain limitations, current research directions, and applications
  • Build GAN to generate images
  • Build another GAN to translate images
  • You will get a deeper understanding on how to apply GANs and adversarial loss to you own deep learning pipeline, in supervised, unsupervised and semi-supervised settings

Pre-workshop reading material

TBD

Learning Material

All participants will have access to the following learning material:

  • Slides from the sessions
  • Hands on notebooks
  • Video recording of the sessions (you can use the videos to watch the parts that you missed, or re-watch any parts that are still unclear for you; access to videos beyond one week after the workshop is available to be purchased; see tickets >> add-ons)

Instructor

Andrew Martin

Head of Data @ Looka Inc

Andrew is a data scientist of 8 years working in deep learning and optimization. He currently leads the data team at Looka where they use generative models like GANs to make great design accessible and delightful to everyone.

Course Modules

The workshop happens on 3 evenings, 3 hours each; each module below will be 50 mins.

Week 1 - Introduction:

  1. Intro to GANs and adversarial training
  2. Writing a GAN
  3. Training your GAN (hands on)

Week 2 - Image to image translation:

  1. Intro to image to image translation GANs
  2. Writing a cycleGAN
  3. Training a cycleGAN (hands on)

Week 3 - Advanced Topics:

  1. Evaluating GANs
  2. Current research and state of the art
  3. Beyond GANs: applications of adversarial training

█░ Kick-starter style

Please note that our technical workshops are run kick-starter style in the sense that they will only happen if a certain amount of funds are raised by the 2-week deadline prior to the event (July 31, 2019):

Funds raised so far to enable the workshop:

█████████░ 87%

Learning Packages

You can customize your learning package. Click on tickets, select your base package (in-person or online), and then tailor your experience the way you want using add-ons.

There is early bird public discount starting at 40% and decreasing by 10% every week until the end of early bird on July 31st, 2019

Discount Codes

There are discount codes available

  • AISC members receive discounts according to their participation credit; refer to the slack channel for more detail

Referral Program

AISC Members, have personalized referral discount codes up to 50% that they can share with their friends and coworkers. Each code can be used 3 times. In order to ensure that people are using the code with your permission they need to enter your email address when registering

Non-members, can enjoy a group discount (10% on top of the current early bird discount) by forming groups of 3+ and registering together. So, go talk to your friends or coworkers right now so that you all save 10% more together.

Refund Policy

Refunds are only available up to 24 hours after the "early bird" deadline: July 31, 2019

Share with friends

Date and Time

Refund Policy

Contact the organizer to request a refund.

Eventbrite's fee is nonrefundable.

Save This Event

Event Saved