Unsupervised, Self-supervised and Reinforcement Learning | SGInnovate

DATE: TBC

Location

BASH, LEVEL 3, 79 AYER RAJAH CRESCENT SINGAPORE 139955

Unsupervised, Self-supervised and Reinforcement Learning

Presented by SGInnovate and Red Dragon AI

Together with Red Dragon AI, SGInnovate is pleased to present the fourth module of the Deep Learning Developer Series. In this module, we dive deeper into the latest Deep Learning techniques such as Unsupervised, Self-supervised and Reinforcement Learning.

About the Deep Learning Developer Series:

The Deep Learning Developer Series is a hands-on series targeted at developers and data scientists, who are looking to build Artificial Intelligence (AI) applications for real-world usage. It is an expanded curriculum that breaks away from the regular 8-week long full-time course structure and allows for modular customisation according to your own pace and preference. In every module, you will have the opportunity to build your own Deep Learning models as part of your main project. You will also be challenged to use your new skills in an application that relates to your field of work or interest.

Start here

    • Have an interest in Deep Learning?
    • Join us if you are able to read and follow codes
    • This module is compulsory before you take the advanced modules
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 AND module 2 OR 3 before this module
     
    • You will need to take module 1, 2 AND 3 before this module
    • Attain a “Deep Learning Specialist” certification when you complete all five modules
     
    • Have an interest in Deep Learning?
    • Join us if you are able to read and follow codes
    • This module is compulsory before you take the advanced modules
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 before this module
     
    • You will need to take module 1 AND module 2 OR 3 before this module
     
    • You will need to take module 1, 2 AND 3 before this module
    • Attain a “Deep Learning Specialist” certification when you complete all five modules
     

About this module:

In this module, we look at some of the latest developments in Deep Learning research, especially promising and interesting advancements in Machine Learning and AI.

One issue with many of the current techniques used in Machine Learning is the requirement for lots of labelled data, which is both costly and time consuming to acquire. Unsupervised and Self-supervised Learning looks at how you can take raw unlabelled data and extract useful insights from that data. There are currently several techniques used to do this, including autoregressive models, representational learning and cycle consistency. We will examine examples each of technique to give you an understanding of how they work and how they can be used and improved further.

We will look at the concept of latent representation and how to extract representational insights from data. We will also touch on techniques such as Generative Adversarial Networks (GANs), tools like Variational Autoencoders (VAEs) and autoregressive models such as Wavenet, PixelRNN and GPT2.

We will also look at the field of Reinforcement Learning (RL) which has driven breakthroughs such as DeepMind’s AlphaGo, Alpha Star and OpenAI’s DOTA models. We will look at how you can examine problems in a game, tackle those problems with a set of algorithms, and how these algorithms can achieve better results than the world’s best human players.

As with all the other Deep Learning Developer modules you will have the opportunity to build multiple models yourself. These include your main project which gives you the ability to take these new skills and apply them to your field of work or interest.

 

This workshop is in the process of applying for funding support.

In this course, participants will learn: 

  • GANs
  • StyleGAN
  • BigGAN
  • CycleGAN
  • InfoGAN
  • VAEs (CVAE, BetaVAE)
  • RL Q Learning
  • Actor Critic Models

Recommended Prerequisites:

This event is co-organised with e2i. e2i administers and acts on behalf of WSG in providing funding to support Singaporeans in enhancing employment and employability, and in the collection, use, processing and/or disclosure of Personal Data, such as NRIC and other national identification documents and numbers, for the purposes of grant administration, validating programme outcomes, fulfilling audit/legal/reporting requirements and analysis of data and statistics and formulating and reviewing of relevant employment or social welfare policies.

 


 

Interested but unable to make it on this date? Leave your details below and we will contact you for the next run.


Dr Martin Andrews
Martin has over 20 years’ experience in Machine Learning and has used it to solve problems in financial modelling and has created AI automation for companies. His current area of focus and speciality is in natural language processing and understanding. In 2017, Google appointed Martin as one of the first 12 Google Developer Experts for Machine Learning. Martin is also one of the co-founders of Red Dragon AI. 

 


Sam Witteveen
Sam has used Machine Learning and Deep Learning in building multiple tech start-ups, including a children’s educational app provider which has over 4 million users worldwide. His current focus is AI for conversational agents to allow humans to interact easier and faster with computers. In 2017, Google appointed Sam as one of the first 12 Google Developer Experts for Machine Learning in the world. Sam is also one of the co-founders of Red Dragon AI. 

Topics: Artificial Intelligence / Deep Learning / Machine Learning / Robotics

You may also like the following: