Subject description - B3B33VIR

Summary of Study | Summary of Branches | All Subject Groups | All Subjects | List of Roles | Explanatory Notes               Instructions
B3B33VIR Robot Learning
Roles:PV Extent of teaching:2P+2L
Department:13133 Language of teaching:CS
Guarantors:  Completion:Z,ZK
Lecturers:  Credits:4
Tutors:  Semester:Z

Web page:

https://cw.fel.cvut.cz/wiki/courses/b3b33vir/start

Anotation:

The course teaches application of machine learning methods and optimization on well-known robotic problems, such as semantic segmenation from RGB-D data or reactive motion control. The core of the course represents teaching of deep learning methods. Stidents will use basic knowledge from optimization and linear algebra such as robut solving of overdetermined systems of (non)linear (non)homogenous equations or gradient minimization methods. The labs are divided into two parts, in the first one, the students will solve basic tasks in PyTorch, in the second one, individual semestral work.

Study targets:

The course teaches application of machine learning methods and optimization on well-known robotic problems, such as semantic segmenation from camera and deep images or reactive robot control. The core of the course represents teaching of deep CNN application methods.

Course outlines:

1. Overview and lecture outline.
2. Regression ML/MAP
3. Classification ML/MAP
4. Neural networks, backpropagation
5. Convolution leyer, backpropagation
6. Normalization leyer (BatchNorm, InstanceNorm, ...) a backpropagation
7. Training I (SGD, momentum and their convergence ratio)
8. Training II (Nester gradient, Adam optimizer, activation function impact on optimization problems)
9. Architectures of deep neural networks I: detection (yolo), segmentation (DeepLab), classification (ResNet)
10. Architectures of deep neural networks II: pose regression, spatial transformer nets.
11. Generative Adversarial Networks, Cascaded Refinement Networks, Style Transfer Networks
12. Reinforcement learning in robotics (policy gradient, imitation learning, actor-critic, aplications)
13. Learning from weak annotations (weak-supervision, self-supervision)
14. Presentation of semestral works

Exercises outline:

In the first half of labs, the students will solve basic tasks in PyTorch, in the second one, the students will work on individual semestral works.

Literature:

Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep learning, MIT press, 2016 http://www.deeplearningbook.org

Requirements:

Keywords:

machine learning, deep neural networks

Subject is included into these academic programs:

Program Branch Role Recommended semester
BPKYR_2016 Common courses PV 5


Page updated 20.7.2024 17:51:28, semester: L/2023-4, Z/2024-5, Z/2023-4, L/2024-5, Send comments about the content to the Administrators of the Academic Programs Proposal and Realization: I. Halaška (K336), J. Novák (K336)