| Title | Time | Room | Instructor |
|---|---|---|---|
| Information Theory (for Data Science) | 27.11.2023 08:45 - 10:00 (Mon) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) | 29.11.2023 08:45 - 10:00 (Wed) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) (recitation) | 30.11.2023 14:45 - 15:45 (Thu) | Sunstone Bldg / Ground floor / Big Seminar Room A / 27 seats (I23.EG.102) | |
| Information Theory (for Data Science) | 04.12.2023 08:45 - 10:00 (Mon) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) | 06.12.2023 08:45 - 10:00 (Wed) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) (recitation) | 07.12.2023 14:45 - 15:45 (Thu) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | |
| Information Theory (for Data Science) | 11.12.2023 08:45 - 10:00 (Mon) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) | 13.12.2023 08:45 - 10:00 (Wed) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) (recitation) | 14.12.2023 14:45 - 15:45 (Thu) | Central Bldg / O1 / Mondi 2a (I01.O1.008) Central Bldg / O1 / Mondi 2b (I01.O1.008) | |
| Information Theory (for Data Science) | 08.01.2024 08:45 - 10:00 (Mon) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) | 10.01.2024 08:45 - 10:00 (Wed) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) (recitation) | 11.01.2024 14:45 - 15:45 (Thu) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | |
| Information Theory (for Data Science) | 15.01.2024 08:45 - 10:00 (Mon) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) | 17.01.2024 08:45 - 10:00 (Wed) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) (recitation) | 18.01.2024 14:45 - 15:45 (Thu) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | |
| Information Theory (for Data Science) | 22.01.2024 08:45 - 10:00 (Mon) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) | 24.01.2024 08:45 - 10:00 (Wed) | Sunstone Bldg / Ground floor / Big Seminar Room B / 63 seats (I23.EG.102) | Esposito, Amedeo Mondelli, Marco |
| Information Theory (for Data Science) (recitation) | 25.01.2024 14:45 - 15:45 (Thu) | Central Bldg / O1 / Mondi 2a (I01.O1.008) Central Bldg / O1 / Mondi 2b (I01.O1.008) |
Description:
The goal of the course is to present fundamental concepts in Information Theory and describe their relevance to emerging problems in Data Science and Machine Learning. Specific topics include basic measures of information, compression and quantization, exponential families, maximum entropy distributions, and elements of statistical learning.
Capacity:
4/30
Course Code:
C_CS-521_F23
Course instructor(s):
Amedeo Esposito
Marco Mondelli
Main Contact:
Marco Mondelli
Course type:
Taught course
Course level:
Advanced/foundational
Primary Track:
Computer Science
Secondary Track(s):
Data Science & Scientific Computing
Course format:
On campus
Classroom requirements:
Blackboard
Capacity for 15-20
Duration:
Half semester
ECTS:
3
Semester:
Fall 2
Minimum number of participants:
1
Target audience:
Interns, PhD students of any year, postdoc, anyone who is interested.
Prerequisites:
Strong background in probability and linear algebra.
Teaching format:
Two lectures per week with regular homeworks.
Grading scheme:
Pass/fail
Course Category:
Credit Course
Academic Year:
AY 2023/24