9. Artificial Intelligence and Neural Networks

9.1 Introduction to AI and Intelligent Agent

• Concept of Artificial Intelligence (AI)
• AI Perspectives
• History of AI and Applications
• Foundations of AI
• Introduction to Agents
  • Structure of Intelligent Agent
  • Properties of Intelligent Agents
  • PEAS Description of Agents
• Types of Agents:
  • Simple Reflexive, Model-Based, Goal-Based, Utility-Based
• Environment Types:
  • Deterministic, Stochastic, Static, Dynamic, Observable, Semi-observable, Single Agent, Multi-Agent

9.2 Problem Solving and Searching Techniques

• Problem Formulation and State Space Search
  • Well-defined Problems, Constraint Satisfaction Problem
• Uninformed Search Techniques:
  • Depth First Search, Breadth First Search, Depth Limited Search, Iterative Deepening Search, Bidirectional Search
• Informed Search:
  • Greedy Best First Search, A* Search, Hill Climbing, Simulated Annealing
• Game Playing and Adversarial Search:
  • Mini-max Search, Alpha-Beta Pruning

9.3 Knowledge Representation

• Knowledge Representation and Mappings
  • Approaches to Knowledge Representation
  • Issues in Knowledge Representation
• Semantic Nets and Frames
• Propositional Logic (PL):
  • Syntax, Semantics, Formal Logic-Connectives, Tautology, Validity, Well-Formed Formula, Inference Using Resolution
• Predicate Logic (FOPL):
  • Syntax, Semantics, Quantification, Rules of Inference, Unification, Resolution Refutation System
• Bayesian Networks:
  • Bayes’ Rule, Reasoning in Belief Networks

9.4 Expert Systems and Natural Language Processing

• Expert Systems:
  • Architecture of Expert Systems, Knowledge Acquisition, Declarative vs Procedural Knowledge, Development of Expert Systems
• Natural Language Processing (NLP):
  • Terminology, Natural Language Understanding and Generation, Steps of NLP
  • Applications and Challenges of NLP
• Machine Vision and Robotics:
  • Concepts, Stages of Machine Vision, Robotics

9.5 Machine Learning

• Introduction to Machine Learning
• Learning Concepts:
  • Supervised, Unsupervised, and Reinforcement Learning
• Types of Learning:
  • Inductive Learning (Decision Tree), Statistical-Based Learning (Naive Bayes Model), Fuzzy Learning
• Fuzzy Inference System and Methods
• Genetic Algorithm:
  • Genetic Algorithm Operators, Encoding, Selection Algorithms, Fitness Function, and Genetic Algorithm Parameters

9.6 Neural Networks

• Biological vs. Artificial Neural Networks (ANN)
• McCulloch-Pitts Neuron and Mathematical Model of ANN
• Activation Functions
• Neural Network Architectures:
  • Perceptron, Learning Rate, Gradient Descent, Delta Rule, Hebbian Learning
  • Adaline Network, Multilayer Perceptron Neural Networks, Backpropagation Algorithm, Hopfield Neural Network