CHAPTER 1: INTRODUCTION TO AI
What is Artificial Intelligence
Types of AI
Perceptron
Multi-Layer Perception
Markov Decision Process
Logical Agent & First Order Logic
AL Applications

CHAPTER 2: ARTIFICIAL INTELLIGENCE FUNDAMENTALS
Application of AI
History of AI
Machine Learning
Fuzzy Logic
Expert Systems
Computer Vision

CHAPTER 3: REINFORCEMENT LEARNING AND Q-LEARNING INTUITION
Q-Learning Introduction
Reinforcement Learning Concepts
Marcov Decision Process
Adding a “Living Penalty”
Temporal Difference
Q-Learning Visualization

CHAPTER 4: DEEP Q-LEARNING INTUITION
Plan of Attack
Deep Q-Learning Intuition – Learning
Experience Replay
Action Selection Policies

CHAPTER 5: CREATING ENVIRONMENT
Installation of environment for Self Driving Car
Building AI
Playing with AI
Challenge Solutions
CHAPTER 6: DEEP CONVENTIONAL Q-LEARNING INTUITION
Plan of Attack
Deep Conventional Q-Learning Intuition
Eligibility Trace
 
CHAPTER 7: ARTIFICIAL INTELLIGENCE AND THEIR TECHNOLOGIES
Human Factors and Evaluation
Information Retrieval & Visualisation
Language & Learning Technology
Vision / Image Processing

CHAPTER 8: ROBOTICS AND ARTIFICIAL INTELLIGENCE
Introduction
Difference between Robotics & AI
Natural Languages Processing (NLP)
Task of NLP
Text Classification
Text Matching
Phonetic Matching
Flexible string Matching
Natural Language Interfaces
Active Computer Vision

CHAPTER 9: PERFORMANCE METRICS
Introduction
Key Methods for Performance Metrics
Confusion Matrix Example
Terms of Confusion Matrix
Accuracy/ Recall / Sensitivity
 
CHAPTER 10: NEURAL NETWORKS
Introduction – Error, Cost & Loss Functions Challenges in Gradient Gradient Descent Techniques to overcome challenges of Mini Batch Convolution Layer and Max-Pooling Hands-on use cases using RNN, LSTM and GRU