# Artificial Intelligence

## by Patrick Winston, Mark Seifter

To listen to an audio podcast, mouse over the title and click Play. Open iTunes to download and subscribe to iTunes U collections.

#### Description

In these lectures, Prof. Patrick Winston introduces the 6.034 material from a conceptual, big-picture perspective. Topics include reasoning, search, constraints, learning, representations, architectures, and probabilistic inference. In these mega-recitations, teaching assistant Mark Seifter works through problems from previous exams in a lecture-style setting. Students are asked to participate, and emphasis is placed on being able to work the algorithms by hand.

Name | Description | Released | Price | ||
---|---|---|---|---|---|

1 | VideoLecture 1: 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. | 11/25/2013 | Free | View In iTunes |

2 | VideoLecture 2: 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. | 11/25/2013 | Free | View In iTunes |

3 | VideoLecture 3: 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. | 11/25/2013 | Free | View In iTunes |

4 | VideoLecture 4: 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. | 11/25/2013 | Free | View In iTunes |

5 | VideoLecture 5: 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. | 11/25/2013 | Free | View In iTunes |

6 | VideoLecture 6: 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. | 11/25/2013 | Free | View In iTunes |

7 | VideoLecture 7: 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. | 11/25/2013 | Free | View In iTunes |

8 | VideoLecture 8: 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. | 11/25/2013 | Free | View In iTunes |

9 | VideoLecture 9: 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. | 11/25/2013 | Free | View In iTunes |

10 | VideoLecture 10: 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. | 11/25/2013 | Free | View In iTunes |

11 | VideoLecture 11: 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. | 11/25/2013 | Free | View In iTunes |

12 | VideoLecture 12: Learning: Neural Nets, Back Propagation | How do we model neurons? In the neural net problem, we want a set of weights that makes the actual output match the desired output. We use a simple neural net to work out the back propagation algorithm, and show that it is a local computation. | 11/25/2013 | Free | View In iTunes |

13 | VideoLecture 13: 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. | 11/25/2013 | Free | View In iTunes |

14 | VideoLecture 14: 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. | 11/25/2013 | Free | View In iTunes |

15 | VideoLecture 15: 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. | 11/25/2013 | Free | View In iTunes |

16 | VideoLecture 16: 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. | 11/25/2013 | Free | View In iTunes |

17 | VideoLecture 17: 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. | 11/25/2013 | Free | View In iTunes |

18 | VideoLecture 18: 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. | 11/25/2013 | Free | View In iTunes |

19 | VideoLecture 19: 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. | 11/25/2013 | Free | View In iTunes |

20 | VideoLecture 21: Probabilistic Inference I | 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. | 11/25/2013 | Free | View In iTunes |

21 | VideoLecture 22: 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. | 11/25/2013 | Free | View In iTunes |

22 | VideoLecture 23: 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. | 11/25/2013 | Free | View In iTunes |

23 | VideoMega-Recitation 1: Rule-Based Systems | 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. | 11/25/2013 | Free | View In iTunes |

24 | VideoMega-Recitation 2: Basic Search, Optimal Search | 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. | 11/25/2013 | Free | View In iTunes |

25 | VideoMega-Recitation 3: Games, Minimax, Alpha-Beta | 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). | 11/25/2013 | Free | View In iTunes |

26 | VideoMega-Recitation 4: Neural Nets | 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. | 11/25/2013 | Free | View In iTunes |

27 | VideoMega-Recitation 5: Support Vector Machines | 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. | 11/25/2013 | Free | View In iTunes |

28 | VideoMega-Recitation 6: Boosting | 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. | 11/25/2013 | Free | View In iTunes |

29 | VideoMega-Recitation 7: Near Misses, Arch Learning | 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. | 11/25/2013 | Free | View In iTunes |

29 Items |

## Customers also subscribed to

- Free
- Category: Computer Science
- Language: English
- http://ocw.mit.edu; Creative Commons Attribution-NonCommercial-ShareAlike 3.0; http://ocw.mit.edu/terms

Discover and share

new apps.

Follow us on @AppStore.

Discover and share new music, movies, TV, books, and more.

Follow us @iTunes and discover

new iTunes Radio Stations

and the music we love.