### Sample Course Schedule (Spring 2014)

Below is a sample schedule, which was the UC Berkeley Spring 2014 course schedule (14 weeks).

The optional readings, unless explicitly specified, come from Artificial Intelligence: A Modern Approach, 3rd ed. by Stuart Russell (UC Berkeley) and Peter Norvig (Google).

The lecture videos for Spring 2014 can be found under the "Video" column here, and additionally, under the Lecture Videos tab along with lecture videos from past semesters.

Under the videos column, there are additional Step-By-Step videos which supplement the lecture's materials. See the list of Step-By-Step videos here.

The links to homework assignments only work when you are logged in to edge.edx.org and are registered for this course. See here for more detailed instructions.

Day | Topic | Optional Reading | Slides | Videos | Assignment | Due |

Tu 1/21 | Introduction to AI | Ch. 1 | PPT | Lecture | P0: Tutorial | 1/24 5pm |

Th 1/23 | Uninformed Search | Ch. 3.1-4 (2e: Ch. 3) | PPT | Lecture SBS-1 |
||

Tu 1/28 | A* Search and Heuristics | Ch. 3.5-6 (2e: Ch. 4.1-2) | PPT | Lecture SBS-2 |
HW1: Search section 0 (solutions) section 1 (solutions) |
2/3 |

Th 1/30 | Constraint Satisfaction Problems I | Ch. 6.1 (2e: Ch. 5.1) | PPT | Lecture | P1: Search | 2/7 5pm |

Tu 2/4 | CSPs II | Ch. 6.2-5 (2e: Ch. 5.2-4) | PPT | Lecture | HW2: CSPs section 2 (solutions) |
2/10 |

Th 2/6 | Game Trees: Minimax | Ch. 5.2-5 (2e: Ch. 6.2-5) | PPT | Lecture SBS-3 |
||

Tu 2/11 | Game Trees: Expectimax; Utilities | Ch. 5.2-5 (2e: Ch. 6.2-5), 16.1-16.3 | PPT | Lecture | HW3: Games section 3 (solutions) |
2/18 |

Th 2/13 | Markov Decision Processes | Ch. 17.1-3 | PPT | Lecture | P2: Multi-Agent Pacman | 2/21 5pm |

Tu 2/18 | Markov Decision Processes II | Ch. 17.1-3, Sutton and Barto Ch. 3-4 | PPT | Lecture | HW4: MDPs section 4 (solutions) |
2/24 |

Th 2/20 | Reinforcement Learning | Ch. 21, S&B Ch. 6.1,2,5 | PPT | Lecture | ||

Tu 2/25 | Reinforcement Learning II | Ch. 21 | PPT | Lecture | HW5: RL section 5 (solutions) |
3/3 |

P3: Reinforcement Learning | 3/7 5pm | |||||

Th 2/27 | Probability | Ch. 13.1-5 (2e: Ch. 13.1-6) | PPT | Lecture | Practice Midterm (solutions) | 3/8 |

Tu 3/4 | Markov Models | Ch. 15.2,5 | PPT | Lecture | ||

Th 3/6 | Hidden Markov Models | Ch. 15.2,5 | PPT | Lecture | ||

Mo 3/10 | Midterm 1 Exam (solutions) | HW6: Probability, HMMs section 6 (solutions) |
3/17 | |||

Th 3/13 | Applications of HMMs | Ch. 15.2,6 | PPT | Lecture | P4: Ghostbusters | 3/21 5pm |

Tu 3/18 | Bayes' Nets: Representation | Ch. 14.1-2,4 | PPT | Lecture | HW7: Bayes' Nets: Representation, Independence section 7 (solutions) |
4/1 |

Th 3/20 | Bayes' Nets: Independence | Ch. 14.1-2,4 | PPT | Lecture SBS-4 |
||

Tu 3/25 | Spring Break | |||||

Th 3/27 | Spring Break | |||||

Tu 4/1 | Bayes' Nets: Inference | Ch. 14.4 | PPT | Lecture SBS-5 SBS-6 |
HW8: Bayes' Nets: Inference, Sampling section 8 (solutions) |
4/7 |

Th 4/3 | Bayes' Nets: Sampling | Ch. 14.4-5 | PPT | Lecture SBS-7 |
||

Tu 4/8 | Decision Diagrams / VPI | Ch. 16.5-6 | PPT | Lecture | HW9: Decision Diagrams, VPI, ML: Naive Bayes section 9 (solutions) |
4/14 |

Practice Midterm 2 (solutions) | 4/19 | |||||

Th 4/10 | ML: Naive Bayes | Ch. 20.1-20.2.2 | PPT | Lecture SBS-8 SBS-9 |
Contest: Pacman Capture the Flag | 4/27 |

Tu 4/15 | ML: Perceptrons | Ch. 18.6.3 | PPT | Lecture SBS-10 |
||

Th 4/17 | ML: Kernels and Clustering | Ch. 18.8 | PPT | Lecture | ||

Mo 4/21 | Midterm 2 Exam (solutions) | HW10: ML: Perceptrons, Kernels section 10 (solutions) section 11 (solutions) |
4/28 | |||

Th 4/24 | Advanced Applications: NLP, Games and Cars | PPT | Lecture | P5: Classification | 5/9 5pm | |

Tu 4/29 | Advanced Applications: (Robotics and Computer Vision) | PPT | Lecture | |||

Th 5/1 | Advanced Topics and Final Contest | PPT | Practice Final (solutions) | 5/10 | ||

Th 5/15 | Final Exam (solutions) |