Artificial Intelligence with Patrick Winston

Video Lectures

Displaying all 30 video lectures.
Lecture 1
Introduction and Scope
Play Video
Introduction and Scope
In this lecture, Prof. Winston introduces artificial intelligence and provides a brief history of the field. The last ten minutes are devoted to information about the course at MIT.
Lecture 2
Reasoning: Goal Trees and Problem Solving
Play Video
Reasoning: Goal Trees and Problem Solving
This lecture covers a symbolic integration program from the early days of AI. We use safe and heuristic transformations to simplify the problem, and then consider broader questions of how much knowledge is involved, and how the knowledge is represented.
Lecture 3
Reasoning: Goal Trees and Rule-Based Expert Systems
Play Video
Reasoning: Goal Trees and Rule-Based Expert Systems
We consider a block-stacking program, which can answer questions about its own behavior, and then identify an animal given a list of its characteristics. Finally, we discuss how to extract knowledge from an expert, using the example of bagging groceries.
Lecture 4
Search: Depth-First, Hill Climbing, Beam
Play Video
Search: Depth-First, Hill Climbing, Beam
This lecture covers algorithms for depth-first and breadth-first search, followed by several refinements: keeping track of nodes already considered, hill climbing, and beam search. We end with a brief discussion of commonsense vs. reflective knowledge.
Lecture 5
Search: Optimal, Branch and Bound, A*
Play Video
Search: Optimal, Branch and Bound, A*
This lecture covers strategies for finding the shortest path. We discuss branch and bound, which can be refined by using an extended list or an admissible heuristic, or both (known as A*). We end with an example where the heuristic must be consistent.
Lecture 6
Search: Games, Minimax, and Alpha-Beta
Play Video
Search: Games, Minimax, and Alpha-Beta
In this lecture, we consider strategies for adversarial games such as chess. We discuss the minimax algorithm, and how alpha-beta pruning improves its efficiency. We then examine progressive deepening, which ensures that some answer is always available.
Lecture 7
Constraints: Interpreting Line Drawings
Play Video
Constraints: Interpreting Line Drawings
How can we recognize the number of objects in a line drawing? We consider how Guzman, Huffman, and Waltz approached this problem. We then solve an example using a method based on constraint propagation, with a limited set of junction and line labels.
Lecture 8
Constraints: Search, Domain Reduction
Play Video
Constraints: Search, Domain Reduction
This lecture covers map coloring and related scheduling problems. We develop pseudocode for the domain reduction algorithm and consider how much constraint propagation is most efficient, and whether to start with the most or least constrained variables.
Lecture 9
Constraints: Visual Object Recognition
Play Video
Constraints: Visual Object Recognition
We consider how object recognition has evolved over the past 30 years. In alignment theory, 2-D projections are used to determine whether an additional picture is of the same object. To recognize faces, we use intermediate-sized features and correlation.
Lecture 10
Introduction to Learning, Nearest Neighbors
Play Video
Introduction to Learning, Nearest Neighbors
This lecture begins with a high-level view of learning, then covers nearest neighbors using several graphical examples. We then discuss how to learn motor skills such as bouncing a tennis ball, and consider the effects of sleep deprivation.
Lecture 11
Learning: Identification Trees, Disorder
Play Video
Learning: Identification Trees, Disorder
In this lecture, we build an identification tree based on yes/no tests. We start by arranging the tree based on tests that result in homogeneous subsets. For larger datasets, this is generalized by measuring the disorder of subsets.
Lecture 12
Neural Nets
Play Video
Neural Nets
*NOTE: These videos were recorded in Fall 2015 to update the Neural Nets portion of the class.



In this video, Prof. Winston introduces neural nets and back propagation.
Lecture 13
Deep Neural Nets
Play Video
Deep Neural Nets
*NOTE: These videos were recorded in Fall 2015 to update the Neural Nets portion of the class.



In this lecture, Prof. Winston discusses BLANK and modern breakthroughs in neural net research.
Lecture 14
Learning: Genetic Algorithms
Play Video
Learning: Genetic Algorithms
This lecture explores genetic algorithms at a conceptual level. We consider three approaches to how a population evolves towards desirable traits, ending with ranks of both fitness and diversity. We briefly discuss how this space is rich with solutions.
Lecture 15
Learning: Sparse Spaces, Phonology
Play Video
Learning: Sparse Spaces, Phonology
Why do "cats" and "dogs" end with different plural sounds, and how do we learn this? We can represent this problem in terms of distinctive features, and then generalize. We end this lecture with a brief discussion of how to approach AI problems.
Lecture 16
Learning: Near Misses, Felicity Conditions
Play Video
Learning: Near Misses, Felicity Conditions
To determine whether three blocks form an arch, we use a model which evolves through examples and near misses; this is an example of one-shot learning. We also discuss other aspects of how students learn, and how to package your ideas better.
Lecture 17
Learning: Support Vector Machines
Play Video
Learning: Support Vector Machines
In this lecture, we explore support vector machines in some mathematical detail. We use Lagrange multipliers to maximize the width of the street given certain constraints. If needed, we transform vectors into another space, using a kernel function.
Lecture 18
Learning: Boosting
Play Video
Learning: Boosting
Can multiple weak classifiers be used to make a strong one? We examine the boosting algorithm, which adjusts the weight of each classifier, and work through the math. We end with how boosting doesn't seem to overfit, and mention some applications.
Lecture 19
Representations: Classes, Trajectories, Transitions
Play Video
Representations: Classes, Trajectories, Transitions
In this lecture, we consider the nature of human intelligence, including our ability to tell and understand stories. We discuss the most useful elements of our inner language: classification, transitions, trajectories, and story sequences.
Lecture 20
Architectures: GPS, SOAR, Subsumption, Society of Mind
Play Video
Architectures: GPS, SOAR, Subsumption, Society of Mind
In this lecture, we consider cognitive architectures, including General Problem Solver, SOAR, Emotion Machine, Subsumption, and Genesis. Each is based on a different hypothesis about human intelligence, such as the importance of language and stories.
Lecture 21
Probabilistic Inference I
Play Video
Probabilistic Inference I
* Please note: Lecture 20, which focuses on the AI business, is not available.




We begin this lecture with basic probability concepts, and then discuss belief nets, which capture causal relationships between events and allow us to specify the model more simply. We can then use the chain rule to calculate the joint probability table.
Lecture 22
Probabilistic Inference II
Play Video
Probabilistic Inference II
We begin with a review of inference nets, then discuss how to use experimental data to develop a model, which can be used to perform simulations. If we have two competing models, we can use Bayes' rule to determine which is more likely to be accurate.
Lecture 23
Model Merging, Cross-Modal Coupling, Course Summary
Play Video
Model Merging, Cross-Modal Coupling, Course Summary
This lecture begins with a brief discussion of cross-modal coupling. Prof. Winston then reviews big ideas of the course, suggests possible next courses, and demonstrates how a story can be understood from multiple points of view at a conceptual level.
Lecture 24
R1. Rule-Based Systems
Play Video
R1. Rule-Based Systems
Instructor: Mark Seifter

In this mega-recitation, we cover Problem 1 from Quiz 1, Fall 2009. We begin with the rules and assertions, then spend most of our time on backward chaining and drawing the goal tree for Part A. We end with a brief discussion of forward chaining.
Lecture 25
R2. Basic Search, Optimal Search
Play Video
R2. Basic Search, Optimal Search
Instructor: Mark Seifter

This mega-recitation covers Problem 2 from Quiz 1, Fall 2008. We start with depth-first search and breadth-first search, using a goal tree in each case. We then discuss branch and bound and A*, and why they give different answers in this problem.
Lecture 26
R3. Games, Minimax, Alpha-Beta
Play Video
R3. Games, Minimax, Alpha-Beta
Instructor: Mark Seifter

This mega-recitation covers Problem 1 from Quiz 2, Fall 2007. We start with a minimax search of the game tree, and then work an example using alpha-beta pruning. We also discuss static evaluation and progressive deepening (Problem 1-C, Fall 2008 Quiz 2).
Lecture 27
R4. Neural Nets
Play Video
R4. Neural Nets
Instructor: Mark Seifter

We begin by discussing neural net formulas, including the sigmoid and performance functions and their derivatives. We then work Problem 2 of Quiz 3, Fall 2008, which includes running one step of back propagation and matching neural nets with classifiers.
Lecture 28
R5. Support Vector Machines
Play Video
R5. Support Vector Machines
Instructor: Mark Seifter

We start by discussing what a support vector is, using two-dimensional graphs as an example. We work Problem 1 of Quiz 4, Fall 2008: identifying support vectors, describing the classifier, and using a kernel function to project points into a new space.
Lecture 29
R6. Boosting
Play Video
R6. Boosting
Instructor: Mark Seifter

This mega-recitation covers the boosting problem from Quiz 4, Fall 2009. We determine which classifiers to use, then perform three rounds of boosting, adjusting the weights in each round. This gives us an expression for the final classifier.
Lecture 30
R7. Near Misses, Arch Learning
Play Video
R7. Near Misses, Arch Learning
Instructor: Mark Seifter

This mega-recitation covers a question from the Fall 2007 final exam, in which we teach a robot how to identify a table lamp. Given a starting model, we identify a heuristic and adjust the model for each example; examples can be hits or near misses.