Artificial intelligence

 

Section 1:

• Why AI?
• Introduction
• How to get data from practice
• Some Additional Resources!!

Section 2: Reinforcement Learning

• Fundamentals of Reinforcement Learning

Section 3: Q-Learning Intuition

• Plan of Attack
• 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

Section 4: Self-Driving Car (Deep Q-Learning) part 1

• Part 1 – An Introduction how Self-Driving Car Works (Deep Q-Learning)

Section 5: Deep Q-Learning Intuition

• Plan of Attack
• Deep Q-Learning Intuition – Learning
• Deep Q-Learning Intuition – Acting
• Experience Replay
• Action Selection Policies

Section 6: Installation for Part 1

• Plan of Attack (Practical Tutorials)
• Where to get the Materials
• 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
• Mac or Linux: Installing Anaconda
• Mac or Linux: Installing PyTorch and Kivy
• Common Debug Tips
• Getting Started

Section 7: Creating the environment

• Self Driving Car – (Step 1 to Step 2)

Section 8: Building an AI

• Self Driving Car – (Step 3 to Step 16)

Section 9: Playing with the AI

• Self Driving Car – (Level 1 to Level 4)
• Challenge Solutions

Section 10: Doom (Deep Convolutional Q-Learning)

• What are convolutional neural networks and Convolutional Q-Learning?

Section 11: Deep Convolutional Q-Learning Intuition

• Plan of Attack
• Deep Convolutional Q-Learning Intuition
• Eligibility Trace

Section 12: Installation for Part 2

• Where to get the Materials
• Installing Open AI Gym and ppaquette
• Installing Open AI Gym Walk through (Mac Version)
• Installing Open AI Gym Walk through (Ubuntu Version)
• Common Debug Tips

Section 13: Building an AI

• Doom – (Step 1 to Step 17)

Section 14: Playing with the AI

• Watching our AI play Doom

Section 15:  A3C

• Introduction

Section 16: A3C Intuition

• Plan of Attack
• The three A’s in A3C
• Actor-Critic
• Asynchronous
• Advantage
• LSTM Layer

Section 17: Installation for Part 3

• Installing OpenCV

Section 18: Building an AI

• Breakout – (Step 1 to Step 15)

Section 19:  Artificial Neural Networks

• 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
• Backpropagation

Section 20: Convolutional Neural Networks

• Plan of Attack
• What are convolutional neural networks?
• Step 1 – Convolution Operation
• Step 1(b) – ReLU Layer
• Step 2 – Pooling
• Step 3 – Flattening
• Step 4 – Full Connection
• Summary
• Softmax & Cross-Entropy