List of Units/Topics

Here is a list of units/topics as they were posted on original class site (for future reference):

Available units:

Final(closed)

Question 1

Question 2

Question 3

Question 4

Question 5

Question 6

Question 7

Question 8

Question 9

Question 10

Question 11

Question 12

22. Natural Language Processing II

Sentence Structure

Parses Question

Problems and Solutions Question

Writing Grammars

PCFG

PCFG Question

Probability Origins

Resolving Ambiguity

LPCFG

Parsing into a Tree

Machine Translation

Translation Example

Optional NLP Programming

Optional Problem

21. Natural Language Processing

Introduction

Language Models

Bag of Words

Probabilistic Models

Language and Learning

Language Models Question

Unigram Model Samples

Bigram Model Samples

Trigram Model Samples

N Gram Model Samples

N Gram Model Question

Probability Question

Language Question

Letter Bigram Question

Trigram Model Question

Classification

Classification Question

Gzip

Segmentation

Segmentation Probabilistic Model

Probabilistic Model Question

Best Segmentation 1

Best Segmentation 2

Segment Code

Segment Question 1

Segment Question 2

Spelling Correction

Spelling Data

Correction Example

Software Engineering

Homework 8(closed)

State Space Question

Dynamic Programming Question 1

Dynamic Programming Question 2

Particle Question 1

Particle Question 2

Stanley Question

Motion Model Question

20. Robotics II

Prediction

Measurement Question

Resampling Question

Planning Question

Road Graph

Cost Question

Dynamic Programming 1

Dynamic Programming 2

Robotic Path Planning

Path Planning Examples

Conclusion

19. Robotics I

Autonomous Vehicle Intro 1

Autonomous Vehicle Intro 2

Robotics Introduction

Robotics Question

Kinematic Question 1

Kinematic Question 2

Dynamic Question

Helicopter Question 1

Helicopter Question 2

Localization

Monte Carlo Localization

Localization Question 1

Localization Question 2

Homework 7(closed)

Perspective Projection

Linear or Not

Gradient Image

Stereo

Correspondence in Stereo

Structure from Motion

18. Computer Vision III

Structure from Motion Question

Projection Question

Structure from Motion Models

SFM Math

Recovered Unknowns Question

Conclusion

17. Computer Vision II

Introduction

Depth Question

Stereo Question

Solving for Depth

Solve Depth Question

Change in X Question

Focal Length Question

Correspondence Question

Determine Correspondence Question

SSD Minimization

Disparity Maps

Context Question

Alignment 1 Question

Alignment 2 Question

Dynamic Programming

Pixel Correspondence Question 1

Pixel Correspondence Question 2

Finding the Best Alignment

Correspondence Issues

Improving Stereo Vision

16. Computer Vision I

Introduction

Image Formation

Projection Length Question

Focal Length Question

Range Question

Perspective Projection

Vanishing Points

Vanishing Points Question

Lenses

Computer Vision

Invariance Question A

Invariance Question B

Invariance Question C

Invariance Question D

Invariance Question E

Final Invariance Type

Importance of Invariance

Greyscale Images

Extracting Features

Extracting Features Question

Linear Filter

Horizontal Edge Question

Vertical Filter Question

Filter Results

Gradient Images

Canny Edge Detector

Other Masks

Prewitt Mask Question

Gaussian Kernel Question

Reasons for Gaussian Kernels

Harris Corner Detector

Modern Feature Detectors

Conclusion

Homework 6(closed)

Max Likelihood Question

Stationary Distribution Question

HMM Question

Particle Filter Question 1

Particle Filter Question 2

Particle Filter Question 3

Particle Filter Question 4

Max Min Question

Scheduling Question

Game Tree Question

Strategy Question

15. Advanced Planning

Introduction

Scheduling

Schedule Question

Resources Question

Extending Planning

Hierarchical Planning

Refinement Planning

Reachable States

Reachable States Question

Conformant Plan Question

Sensory Plan Question

14. Game Theory

Introduction

Dominant Strategy Question

Pareto Optimal Question

Equilibrium Question

Game Console Question 1

Game Console Question 2

2 Finger Morra

Tree Question

Mixed Strategy

Solving the Game

Mixed Strategy Issues

2x2 Game Question 1

2x2 Game Question 2

Geometric Interpretation

Poker

Game Theory Strategies

Fed vs Politicians Question

Mechanism Design

Auction Question

13. Games

Introduction

Technologies Question

Games Question

Single Player Game

Two Player Game

Two Player Function

Time Complexity Question

Space Complexity Question

Chess Question

Complexity Reduction Question

Review Question

Reduce B

Reduce B Question

Reduce M

Computing State Values

Complexity Reduction Benefits

Pacman Question

Chance

Chance Question

Terminal State Question

Game Tree Question 1

Game Tree Question 2

Conclusion

Midterm(closed)

Question 01

Question 02

Question 03

Question 04

Question 05

Question 06

Question 07

Question 08

Question 09

Question 10

Question 11

Question 12

Question 13

Question 14

Question 15

12. MDP Review

Deterministic Question

Single Backup Question

Convergence Question

Optimal Policy Question

11. HMMs and Filters

Introduction

Hidden Markov Models

Bayes Network of HMMs

Localization Problem Examples

Markov Chain Question 1

Markov Chain Question 2

Stationary Distribution

Stationary Distribution Question-

Finding Transition Probabilities

Transition Probabilities Question

Laplacian Smoothing Question

HMM Happy Grumpy Problem

Happy Grumpy Question

Wow You Understand

HMMs and Robot Localization

HMM Equations

HMM Localization Example

Particle Filters

Localization and Particle Filters

Particle Filter Algorithm

Particle Filters Pros and Cons

Conclusion

Homework 5(closed)

Q Learning

Function Generalization

Passive RL Agent

10. Reinforcement Learning

Introduction

Successes

Forms of Learning

Forms of Learning Question

MDP Review

Solving a MDP

Agents of Reinforcement Learning

Passive vs Active

Passive Temporal Difference Learning

Passive Agent Results

Weaknesses Question

Active Reinforcement Learning

Greedy Agent Results

Balancing Policy

Errors in Utility Questions

Exploration Agents

Exploration Agent Results

Q Learning 1

Q Learning 2

Pacman 1

Pacman 2

Conclusion

9. Planning under Uncertainty

Introduction

Planning Under Uncertainty MDP

Robot Tour Guide Examples

MDP Grid World

Problems with Conventional Planning 1

Branching Factor Question

Problems with Conventional Planning 2

Policy Question 1

Policy Question 2

Policy Question 3

Policy Answer 3 Question 4

MDP and Costs

Value Iteration 1

Value Iteration 2

Value Iteration 3

Deterministic Question 1

Deterministic Question 2

Deterministic Question 3

Stochastic Question 1

Stochastic Question 2

Value Iterations and Policy 1

Value Iterations and Policy 2

MDP Conclusion

Partial Observability Introduction

POMDP vs MDP

POMDP

Planning Under Uncertainty Conclusion

Homework 4(closed)

Logic

More Logic

Vacuum World

More Vacuum World

Monkey and Bananas

Situation Calculus

8. Planning

Introduction

Problem Solving vs Planning

Planning vs Execution

Vacuum Cleaner Example

Sensorless Vacumm Cleaner Problem-

Partially Observable Vacuum Cleaner Example

Stocastic Environment Problem

Infinite Sequences

Finding a Successful Plan-

Finding a Successful Plan Question

Problem Solving via Mathematical Notation

Tracking the Predict Update Cycle

Classical Planning 1

Classical Planning 2

Progression Search

Regression Search

Regression vs Progression

Plan Space Search

Sliding Puzzle Example

Situation Calculus 1

Situation Calculus 2

Situation Calculus 3

7. Representation with Logic

Introduction

Propositional Logic

Truth Tables

Question

Terminology

Propositional Logic Limitations

First Order Logic

Models

Syntax

Vacuum World

Question

Homework 3(closed)

Naive Bayes

Naive Bayes 2

Maximum Likelihood

Linear Regression

Linear Regression 2

K Nearest Neighbors

K Nearest Neighbors 2

Perceptron

6. Unsupervised Learning

Unsupervised Learning

Question

Terminology

Google Street View and Clustering

k-Means Clustering Example

k-Means Algorithm

Question

Expectation Maximization

Gaussian Learning

Maximum Likelihood

Question

Gaussian Summary

EM as Generalization of k-Means

EM Algorithm

Question

Choosing k

Clustering Summary

Dimensionality Reduction

Question

Linear Dimensionality Reduction

Face Example

Scan Example

Piece-Wise Linear Projection

Spectral Clustering

Spectral Clustering Algorithm

Question

Supervised vs Unsupervised Learning

5. Machine Learning

Introduction

What is Machine Learning

Stanley DARPA Grand Challenge

Taxonomy

Supervised Learning

Occam's Razor

SPAM Detection

Question

Maximum Likelihood_1

Relationship to Bayes Networks

Question

Answer and Laplace Smoothing

Question

Summary Naive Bayes

Advanced SPAM Filtering

Digit Recognition

Overfitting Prevention

Classification vs Regression

Linear Regression

More Linear Regression

Quadratic Loss

Problems with Linear Regression

Linear Regression and Complexity Control

Minimizing Complicated Loss Functions

Question

Answer

Gradient Descent Implementation

Perceptron

k Nearest Neighbors

kNN Definition

k as Smoothing Parameter

Problems with kNN

Congratulations

Homework 2(closed)

Bayes Rule

Simple Bayes Net

Simple Bayes Net 2

Conditional Independence

Conditional Independence 2

Parameter Count

4. Probabilistic Inference

Overview and Example

Enumeration

Speeding Up Enumeration

Speeding Up Enumeration 2

Speeding Up Enumeration 3

Speeding Up Enumeration 4

Causal Direction

Variable Elimination

Variable Elimination 2

Variable Elimination 3

Variable Elimination 4

Approximate Inference

Sampling Example

Approximate Inference 2

Rejection Sampling

Likelihood Weighting

Likelihood Weighting 1

Likelihood Weighting 2

Gibbs Sampling

Monty Hall Problem

Monty Hall Letter

3. Probability in AI

Introduction

Probability/Coin Flip

Coin Flip 2

Coin Flip 3

Coin Flip 4

Coin Flip 5

Probability Summary

Dependence

What We Learned

Weather

Weather 2

Weather 3

Cancer

Cancer 2

Cancer 3

Cancer 4

Bayes Rule

Bayes Network

Computing Bayes Rule

Two Test Cancer

Two Test Cancer 2

Conditional Independence

Conditional Independence 2

Absolute and Conditional

Confounding Cause

Explaining Away

Explaining Away 2

Explaining Away 3

Conditional Dependence

General Bayes Net

General Bayes Net 2

General Bayes Net 3

Value of a Network

D-Separation

D-Separation 2

D-Separation 3

Congratulations!

Homework 1(closed)

Peg Solitaire

Loaded Coin

Maze

Search Tree

Search Tree 2

Search Network

A* Search

2. Problem Solving

Introduction

What is a Problem?

Example: Route Finding

Tree Search

Tree Search Continued

Graph Search

Breadth First Search 1

Breadth First Search 2

Breadth First Search 3

Breadth First Search 4

Breadth First Search 5

Uniform Cost Search

Uniform Cost Search 1

Uniform Cost Search 2

Uniform Cost Search 3

Uniform Cost Search 4

Uniform Cost Search 5

Search Comparison

Search Comparison 1

Search Comparison 2

Search Comparison 3