Machine learning allows computational systems to adaptively improve their performance with experience accumulated from the data observed. This course introduces the basics of learning theories, the design and analysis of learning algorithms, and some applications of machine learning.
| date | syllabus | todo/done | materials |
| 09/09 (W1) |
course introduction;
topic 1: when can machines learn?
|
homework 0 announced |
|
| 09/16 (W2) |
the learning problem;
learning to answer yes/no;
types of learning
|
|
required watching (before class):
required watching (before class):
required watching (before class):
other materials:
|
| 09/23 (W3) |
types of learning;
feasibility of learning;
topic 2: why can machines learn?
training versus testing
|
homework 1 announced |
required watching (before class):
required watching (before class):
required watching (before class):
other materials:
suggested extended reading:
|
| 09/30 (W4) |
training versus testing;
(optional)theory of generalization;
the VC dimension;
noise and error
|
|
required watching (before class):
suggested watching (anytime):
required watching (before class):
required watching (before class):
other materials:
|
| 10/07 (W5) |
topic 3: how can machines learn?
linear regression;
logistic regression
|
homework 2 announced |
|
| 10/14 (W6) |
linear models for classification;
nonlinear transformation
|
final project announced (tentative) |
|
| 10/21 (W7) |
topic 4: how can machines learn better?
hazard of overfitting;
regularization
|
homework 0 due; homework 1 due; homework 2 due; homework 3 announced
|
|
| 10/28 (W8) |
validation;
three learning principles
|
|
|
| 11/04 (W9) |
topic 5: how can machines learn by embedding numerous features?
linear support vector machine;
dual support vector machine
|
homework 3 due; homework 4 announced
|
|
| 11/11 (W10) |
kernel support vector machine;
soft-margin support vector machine
|
|
|
| 11/18 (W11) |
topic 6: how can machines learn by combining predictive features?
blending and bagging;
adaptive boosting
|
homework 4 due; homework 5 announced
|
|
| 11/25 (W12) |
decision tree;
random forest;
gradient boosted decision tree
|
|
|
| 12/02 (W13) |
no class as instructor needs to attend ACML 2025 and NeurIPS 2026;
|
homework 5 due; homework 6 announced
|
|
| 12/09 (W14) |
FINAL EXAM!!!;
|
|
|
| 12/16 (W15) |
topic 7: how can machines learn by distilling hidden features?
neural network;
deep learning
|
|
|
|
| 12/23 (W16) |
modern deep learning;
finale
|
homework 6 due
|
|
| 12/30 (W17) |
no class and winter vacation started (really?) |
final project due (tentative) |
|
