|
HU Credits:
4
Degree/Cycle:
2nd degree (Master)
Responsible Department:
Computer Sciences
Semester:
1st Semester
Teaching Languages:
English and Hebrew
Campus:
E. Safra
Course/Module Coordinator:
Amit Daniely
Coordinator Office Hours:
Teaching Staff:
Dr.
Course/Module description:
The course will discuss learning from a computational and statistical standpoints. We will assume familiarity with machine learning (e.g. 67577), and will deepen our theoretical and mathematical understanding of the matter.
We will discuss questions such as: Which functions are learnable? How? How many resources are needed? When do specific learning algorithms succeed? How to design a learning algorithm for a given task?
Course/Module aims:
To introduce the scope and the goals of learning theory, and to understand basic techniques and results.
Learning outcomes - On successful completion of this module, students should be able to:
Read professional literature and research papers in learning theory. Do research in learning theory.
Attendance requirements(%):
None
Teaching arrangement and method of instruction:
Frontal lectures, Homework
Course/Module Content:
1. Functions classes: Separation results and Algorithms
2. Statistical Learning Theory: Uniform Convergence, VC dimension, Radamacher complexity, Stability
3. Online Learning and Online Convex Optimization
4. Computational Learning Theory: Hardness of learning, The statistical queries model
5. Glimpse into neural networks and deep learning
Required Reading:
None
Additional Reading Material:
Will be published during the course
Grading Scheme :
Additional information:
|
