ï‚· No
class on September 3 due to Labor Day.
ï‚· No
class on November 21 due to Thanksgiving.
Two
important notes:
1. The lecture
schedule below is tentative and subject to change. We will move at a pace
dictated by class discussions.
2. The slides from Mitchell's book are a good summary of that
book but usually not of my lectures.
Topics |
Tentative Dates (Click to watch
video) Livestream |
Reading |
Reading from Murphy |
Notes & Other
Material |
Lecture Recordings from
Fall 2017
|
Course goals, philosophy, teaching style, policies and mechanics
|
|
|
|
||
Introduction: The Machine Learning Process |
CH 1 |
CH
1 |
|||
Concept learning, inductive bias |
CH 2 (excluding 2.5.3, 2.6.3) |
CH
3.1, 3.2 |
|||
Information Theory |
|
CH
2.8 |
|||
Decision trees, overfitting, Occam's razor |
CH 3 |
CH
16.2 |
|||
Review of Prob & Stats. Linear Regression |
|
CH
2.2, 2.5, CH 7 |
|||
Mid-term exam |
Monday 10/15 at 6:30pm - 9:30pm LOCATION: DH 2315 and McConomy |
|
|
Important tip: Try to solve this
exam in writing before you look at the solutions. |
|
Neural Networks; Deep Learning |
CH 4 |
CH
16.5, CH 28 |
Very
clear overview of Deep Learning, Zack's Deep Learning Slides |
||
Bayesian learning, MAP and ML |
CH 6 slides |
CH 5.1--5.4 |
|||
Naive Bayes |
CH
6 |
CH
3.5 |
|||
Undirected Graphical Models (MRFs), Hidden Markov Models, Directed Graphical Models (Bayes Nets) |
CH 6 |
CH
10, CH 19, CH 5.3.2.4, CH 17, Online Intro |
Wayne Ward's slides |
||
Reinforcement Learning |
|
|
|
|
|
EM Algorithm |
CH 6 |
CH
11 |
|||
Instance based (non-parametric) learning, KNN |
CH 8 slides |
CH
14.1--14.3 |
|||
Kernel Based methods, Maximum-Margin Classifiers, misc. |
CH
14.4, CH 14.5 |
||||
Recitation/Review |
|
|
|||
FINAL EXAM |
December 13th at 1:00pm-4:00pm |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
||
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|