Weizmann Institute of Science


Deep Learning for Computer Vision:
Fundamentals and Applications

Winter 2022/3

[Home | Schedule | Final Project | Moodle]

Course Overview

This course covers the fundamentals of deep-learning based methodologies in area of computer vision. Topics include: core deep learning algorithms (e.g., convolutional neural networks, transformers, optimization, back-propagation), and recent advances in deep learning for various visual tasks. The course provides hands-on experience with deep learning for computer vision: implementing deep neural networks and their components from scratch, tackling real world tasks in computer vision by desigining, training, and debugging deep neural networks using leading mainly PyTorch.


Course Information

Course Instructors

Teaching Assistants

Dror Moran
Rafail Fridman
Dana Joffe
Yaniv Nikankin

Please use the course Moodle page for all communication with the teaching staff.

Lectures and tutorials time

Lectures: 9:15-11:00 on Mondays

Tutorials: 9:15-11:00 on Wednesdays

Office Hours

Upon request

Grading Policy

Final grade will be given based on assignments and a final project.
There will be no exam in the course.
Note that different assignments might have different cntribution to the overall grade.

Previous semesters

Winter 2021/2.

Spring 2021.



The template of this website is based on CSAIL MIT's Advanced Computer Vision course