Artificial Intelligence (AI), Deep Learning (DL) and Machine Learning (ML)
Hands-on Workshop – 5 days

Complete beginner to expert AI skills
MAY 13th, 2018 

Overview:

This is a great training to encompass the recent evolutions of AI.

It explains why AI is powerful today and then illustrate how to apply it with a very powerful framework on examples like a self-driving car prototype or the game "Doom". The examples are easy to understand and you navigate in the programming side step by step. The results of the programs are discussed so that you can also get a flavor of AI current limitations and its potential of extra evolution. You "just" need afterwards to imagine the rest to extrapolate in real-world situations.

Target Audience:

Anyone interested in Artificial Intelligence, Machine Learning or Deep Learning

Pre-requisite:

  • Only High School Math
  • Some programming language structure (Python preferred)

Learning Outcomes:

  • Build an AI
  • Understand the theory behind Artificial Intelligence
  • Make a virtual Self Driving Car
  • Make an AI to beat games
  • Solve Real World Problems with AI
  • Master the State of the Art AI models
  • Q-Learning
  • Deep Q-Learning
  • Deep Convolutional Q-Learning
  • A3C
  • Project:
    • Make a virtual Self Driving Car
    • Make an AI to beat games
    • DOOM
  • What is reinforcement learning?
  • The Bellman Equation
  • The "Plan"
  • Markov Decision Process
  • Policy vs Plan
  • Adding a "Living Penalty"
  • Q-Learning Intuition
  • Temporal Difference
  • Q-Learning Visualization
  • Plan of Attack
  • Deep Q-Learning Intuition - Learning
  • Deep Q-Learning Intuition - Acting
  • Experience Replay
  • Action Selection Policies
  • Installation for Part 1
  • Plan of Attack (Practical Tutorials)
  • Windows Option 1: End-to-End installation steps
  • Windows Option 2 - Part A: Installing Ubuntu on Windows
  • Windows Option 2 - Part B: Installing PyTorch and Kivy on your Ubuntu VM
  • Self-Driving Car - Step 1 – 16
  • Plan of Attack
  • Deep Convolutional Q-Learning Intuition
  • Eligibility Trace
  • Installation for Part 2
  • Installing Open AI Gym and ppaquette
  • Doom - Step 1 – 17
  • Watching our AI play Doom
  • A3C Intuition
  • Plan of Attack
  • The three A's in A3C
  • Actor-Critic
  • Asynchronous
  • Advantage
  • LSTM Layer
  • Building an AI Hands-on Project
  • Installing OpenCV
  • Building an AI
  • Breakout - Step 1 – 15
  • What is Deep Learning?
  • Plan of Attack
  • The Neuron
  • The Activation Function
  • How do Neural Networks work?
  • How do Neural Networks learn?
  • Gradient Descent
  • Stochastic Gradient Descent
  • Back propagation
  • What are convolutional neural networks?
  • Step 1 - Convolution Operation
  • Step 1(b) - ReLU Layer
  • Step 2 - Pooling
  • Step 3 - Flattening
  • Step 4 - Full Connection

Description

Learn key AI concepts and intuition training to get you quickly up to speed with all things AI. Covering:

•How to start building AI with no previous coding experience using Python

•How to merge AI with OpenAI Gym to learn as effectively as possible

•How to optimize your AI to reach its maximum potential in the real world

 

What you will get with this course:

  • Complete beginner to expert AI skills – Learn to code self-improving AI for a range of purposes. In fact, we code together with you. Every tutorial starts with a blank page and we write up the code from scratch. This way you can follow along and understand exactly how the code comes together and what each line means.
  • Code templates – Plus, you’ll get source code templates for every AI you build in the course. This makes building truly unique AI as simple as changing a few lines of code. If you unleash your imagination, the potential is unlimited.
  • Intuition Lectures – Where most courses simply bombard you with dense theory and set you on your way, we believe in developing a deep understanding for not only what you’re doing, but why you’re doing it. The course focuses on building up your intuition in coding AI making for infinitely better results down the line.
  • Real-world solutions – You’ll achieve your goal in hands-on. Each module is comprised of varying structures and difficulties, meaning you’ll be skilled enough to build AI adaptable to any environment in real life, rather than just passing a “test and forget”. Practice truly does make perfect.
  • In-course support – We’re fully committed to making this the most accessible and results-driven AI course on the planet. This requires us to be there when you need our help.

Course Contents

Why AI? - Introduction

Part 1 - Fundamentals of Reinforcement Learning

Welcome to Part 1 - Fundamentals of Reinforcement Learning

Q-Learning Intuition

Part 2 - Self-Driving Car (Deep Q-Learning)

Welcome to Part 2 - Self-Driving Car (Deep Q-Learning)

Deep Q-Learning Intuition

 

Creating the environment

Building an AI Hands-on Project

Playing with the AI (Testing and driving the car)

Challenge Solutions

Part 3 - Doom (Deep Convolutional Q-Learning)

 

Deep Convolutional Q-Learning Intuition

These resources are intended to walk you through setting up Open AI Gym in addition to common solutions for debugging. Students will learn additional information about operating and installing packages in the terminal.

Building an AI Hands-on Project

Playing with the AI (Testing and playing Doom)

Part 4 - Breakout (A3C)

 

Annex 1: Artificial Neural Networks

Annex 2: Convolutional Neural Networks

Summary

Softmax & Cross-Entropy 

HURRY UP! Limited seats available

Contact Us