InfoCoBuild

An Introduction to Artificial Intelligence

An Introduction to Artificial Intelligence. Instructor: Prof. Mausam, Department of Computer Science and Engineering, IIT Delhi. The course introduces the variety of concepts in the field of artificial intelligence. It discusses the philosophy of AI, and how to model a new problem as an AI problem. It describes a variety of models such as search, logic, Bayes nets, and MDPs, which can be used to model a new problem. It also teaches many first algorithms to solve each formulation. The course prepares a student to take a variety of focused, advanced courses in various subfields of AI. (from nptel.ac.in)

Lecture 82 - Reinforcement Learning: Exploration vs Exploitation Tradeoff

Go to the Course Home or watch other lectures:

Lecture 01 - Introduction: What to Expect from AI

Lecture 02 - Introduction: History of AI from 40s to 90s

Lecture 03 - Introduction: History of AI in 90s

Lecture 04 - Introduction: History of AI in NASA and DARPA (2000s)

Lecture 05 - Introduction: The Present State of AI

Lecture 06 - Introduction: Definition of AI Dictionary Meaning

Lecture 07 - Introduction: Definition of AI Thinking vs Acting and Humanly vs Rationally

Lecture 08 - Introduction: Definition of AI Rational Agent View of AI

Lecture 09 - Introduction: Examples Tasks, Phases of AI and Course Plan

Lecture 10 - Uniform Search: Notion of a State

Lecture 11 - Uniform Search: Search Problem and Examples Part-2

Lecture 12 - Uniform Search: Basic Search Strategies Part-3

Lecture 13 - Uniform Search: Iterative Deepening DFS Part-4

Lecture 14 - Uniform Search: Bidirectional Search Part-5

Lecture 15 - Informed Search: Best First Search Part-1

Lecture 16 - Informed Search: Greedy Best First Search and A* Search Part-2

Lecture 17 - Informed Search: Analysis of A* Algorithm Part-3

Lecture 18 - Informed Search: Proof of Optimality of A* Algorithm Part-4

Lecture 19 - Informed Search: Iterative Deepening A* and Depth First Branch and Bound Part-5

Lecture 20 - Informed Search: Admissible Heuristics and Domain Relaxation Part-6

Lecture 21 - Informed Search: Pattern Database Heuristics Part-7

Lecture 22 - Local Search: Satisfaction vs Optimization Part-1

Lecture 23 - Local Search: The Example of N-Queens Part-2

Lecture 24 - Local Search: Hill Climbing Part-3

Lecture 25 - Local Search: Drawbacks of Hill Climbing Part-4

Lecture 26 - Local Search of Hill Climbing with Random Walk and Random Restart Part-5

Lecture 27 - Local Search: Hill Climbing with Simulated Annealing Part-6

Lecture 28 - Local Search: Local Beam Search and Genetic Algorithms Part-7

Lecture 29 - Adversarial Search: Minimax Algorithm for Two Player Games

Lecture 30 - Adversarial Search: An Example of Minimax Search

Lecture 31 - Adversarial Search: Alpha Beta Pruning

Lecture 32 - Adversarial Search: Analysis of Alpha Beta Pruning

Lecture 33 - Adversarial Search: Analysis of Alpha Beta Pruning (cont.)

Lecture 34 - Adversarial Search: Horizon Effect, Game Databases and Other Ideas

Lecture 35 - Adversarial Search: Summary and Other Games

Lecture 36 - Constraint Satisfaction Problems: Representation of the Atomic State

Lecture 37 - Constraint Satisfaction Problems: Map Coloring and Other Examples of CSP

Lecture 38 - Constraint Satisfaction Problems: Backtracking Search

Lecture 39 - Constraint Satisfaction Problems: Variable and Value Ordering in Backtracking Search

Lecture 40 - Constraint Satisfaction Problems: Inference for Detecting Failures Early

Lecture 41 - Constraint Satisfaction Problems: Exploiting Problem Structure

Lecture 42 - Logic in AI: Different Knowledge Representation Systems - Part 1

Lecture 43 - Logic in AI: Syntax - Part 2

Lecture 44 - Logic in AI: Semantics - Part 3

Lecture 45 - Logic in AI: Forward Chaining - Part 4

Lecture 46 - Logic in AI: Resolution - Part 5

Lecture 47 - Logic in AI: Reduction to Satisfiability Problems - Part 6

Lecture 48 - Logic in AI: SAT Solvers: DPLL Algorithm - Part 7

Lecture 49 - Logic in AI: SAT Solvers: WalkSAT Algorithm - Part 8

Lecture 50 - Uncertainty in AI: Motivation

Lecture 51 - Uncertainty in AI: Basics of Probability

Lecture 52 - Uncertainty in AI: Conditional Independence and Bayes Rule

Lecture 53 - Bayesian Networks: Syntax

Lecture 54 - Bayesian Networks: Factorization

Lecture 55 - Bayesian Networks: Conditional Independences and d-Separation

Lecture 56 - Bayesian Networks: Inference using Variable Elimination

Lecture 57 - Bayesian Networks: Reducing 3-SAT to Bayes Net

Lecture 58 - Bayesian Networks: Rejection Sampling

Lecture 59 - Bayesian Networks: Likelihood Weighting

Lecture 60 - Bayesian Networks: MCMC with Gibbs Sampling

Lecture 61 - Bayesian Networks: Maximum Likelihood Learning

Lecture 62 - Bayesian Networks: Maximum a-Posteriori Learning

Lecture 63 - Bayesian Networks: Bayesian Learning

Lecture 64 - Bayesian Networks: Structure Learning and Expectation Maximization

Lecture 65 - Introduction: Agents and Environments

Lecture 66 - Decision Theory: Steps in Decision Theory

Lecture 67 - Decision Theory: Non-deterministic Uncertainty

Lecture 68 - Probabilistic Uncertainty and Value of Perfect Information

Lecture 69 - Expected Utility vs Expected Value

Lecture 70 - Markov Decision Processes: Definition

Lecture 71 - Markov Decision Processes: An Example of a Policy

Lecture 72 - Markov Decision Processes: Policy Evaluation using System of Linear Equations

Lecture 73 - Markov Decision Processes: Iterative Policy Evaluation

Lecture 74 - Markov Decision Processes: Value Iteration

Lecture 75 - Markov Decision Processes: Policy Iteration and Applications and Extensions of MDPs

Lecture 76 - Reinforcement Learning: Background

Lecture 77 - Reinforcement Learning: Model-based Learning for Policy Evaluation (Passive Learning)

Lecture 78 - Reinforcement Learning: Model-free Learning for Policy Evaluation (Passive Learning)

Lecture 79 - Reinforcement Learning: TD Learning

Lecture 80 - Reinforcement Learning: TD Learning and Computational Neuroscience

Lecture 81 - Reinforcement Learning: Q Learning

Lecture 82 - Reinforcement Learning: Exploration vs Exploitation Tradeoff

Lecture 83 - Reinforcement Learning: Generalization in RL

Lecture 84 - Deep Learning: Perceptrons and Activation Functions

Lecture 85 - Deep Learning: Example of Handwritten Digit Recognition

Lecture 86 - Deep Learning: Neural Layer as Matrix Operations

Lecture 87 - Deep Learning: Differentiable Loss Function

Lecture 88 - Deep Learning: Backpropagation through a Computational Graph

Lecture 89 - Deep Learning: Thin Deep vs Fat Shallow Networks

Lecture 90 - Deep Learning: Convolutional Neural Networks

Lecture 91 - Deep Learning: Deep Reinforcement Learning

Lecture 92 - Ethics of AI: Humans vs Robots

Lecture 93 - Ethics of AI: Robustness and Transparency of AI Systems

Lecture 94 - Ethics of AI: Data Bias and Fairness of AI Systems

Lecture 95 - Ethics of AI: Accountability, Privacy and Human-AI Interaction

Lecture 96 - Wrapup