Red Dragon Logo

Unsupervised, Self Supervised and Reinforcement Learning

This two day workshop is designed to give participants an understanding of the the current cutting edge methods, models and techniques used in Unsupervised, Self Supervised and Reinforcement Learning. This includes looking at AutoEncoders, General Adversarial Networks and a variety of Reinforcement Learning techniques.

What You'll Learn

  • Building networks such as Resnets & Inception Networks
  • Building GANs from scratch
  • Understanding various types of AutoEncoders
  • Solving Atari games with Deep Q Networks
  • How to use Latent Spaces for generation
  • Understanding from AlphaGo through MuZero

Course Overview

This 4th module in the series looks at some of the latest developments in Deep Learning research, it will cover what is cutting edge and what currently looks most promising and interesting for the advancements in Machine Learning and AI.

One issue with many of the current techniques used in Machine Learning is the requirement for lots of labeled data, which is both costly and time consuming to create. Unsupervised and Self-Supervised Learning looks at how you can take raw unlabeled data and extract useful learnings from that data. There are currently a number of promising techniques used to do this that include Autoregressive models, Representational Learning and Cycle Consistency. We will examine examples of each of these and more to give the student an understanding of how they work as techniques, and inspire how they could be used or improved upon.

We look at a variety of techniques such as Generative Adversarial Networks and how they are being used to produce realistic and lifelike examples, such as generated pictures of faces. Other types of techniques we will examine are Autoregressive models such as Wavenet, PixelRNN and GPT3 and how they create self labeling systems and Variational Auto-Encoders and the concepts of latent representations and extracting representational learnings from data.

We will also look at the field of Reinforcement Learning which has born breakthroughs such as DeepMind’s AlphaGo, Alpha Star and OpenAI’s DOTA models. We will look at how participants can examine problems as a game, which can be learnt to be played by a set of algorithms and how those algorithms can often achieve results better than the world’s best human players.

Key techniques covered:

  • Unsupervised Learning
  • Representational Learning
  • Auto Regressive Self Supervised Learning
  • Reinforcement Learning
  • Contrastive Learning
  • Generative Adversarial techniques
  • Cycle Consistency

Some of the models we will look at include:

  • Generative Adversarial Networks
  • StyleGANv2
  • BigGAN, InfoGAN, DCGAN, CycleGAN
  • Auto encoders, VAEs (CVAE, BetaVAE)
  • Q Learning, DQN, DDQN,
  • Actor Critic Models, PPO
  • Multi Agent RL Systems


2 days live + 7 hours online


$1800 per pax


A solid understanding of Deep Learning and TensorFlow

Technologies we teach will include:


Earn a certificate upon completion

Training Level

Intermediate Level

Time to Complete

Approx. 21 hours to complete

Why Study Artificial Inteligence?

1. Demand for AI/Dl jobs has never been at this all time high.

2. Developers need these skills

3. AI/DL Jobs pay more than standard developer jobs

Comp Screen

Request More Info

Sign up to receive additional information about this course. Find out what other learners are doing with the skills they gamed, and evaluate if this course is the right fit for you.

Comp Screen

Frequently Asked Questions

Do I have to log in at a set time? How does the 360-degree assessment work? At this point, you probably have a few questions, and we’ve got answers.

About RDAI

Coming Soon


2022-2023© All Rights Reserved