Robot Learning
| Code | Completion | Credits | Range | Language |
|---|---|---|---|---|
| B3B33UROB | Z,ZK | 6 | 2P+2C | Czech |
- Vztahy:
- It is not possible to register for the course B3B33UROB if the student is concurrently registered for or has already completed the course B3B33VIR (mutually exclusive courses).
- During a review of study plans, the course B3B33VIR can be substituted for the course B3B33UROB.
- It is not possible to register for the course B3B33UROB if the student is concurrently registered for or has previously completed the course B3B33VIR (mutually exclusive courses).
- Garant předmětu:
- Karel Zimmermann
- Lecturer:
- Karel Zimmermann
- Tutor:
- David Čapek, Aleš Kučera, Tomáš Tichý, Patrik Vacek, Jan Vlk, Karel Zimmermann
- Supervisor:
- Department of Cybernetics
- Synopsis:
-
The course teaches deep learning methods on known robotic problems, such as semantic segmenation or reactive motion control. The overall goal is timeless universal knowledge rather than listing all known deep learning architectures. Students are assumed to have working prior knowledge of mathematics (gradient, jacobian, hessian, gradient descend, taylor polynomial) and machine learning (bayes risk minimization, linear classifier). The labs are divided into two parts, in the first one, the students will solve elementary deep ML tasks from scratch (including the reimplementation of autograd backpropagation), in the second one, students will build on existing templates in order to solve complex tasks including RL, tranformers and generative networks.
- Requirements:
- Syllabus of lectures:
-
Machine learning 101: model, loss, learning, issues, regression, classification
Under the hood of a linear classifier: two-class and multi-class linear classifier on RGB images
Under the hood of auto-differentiation: Computational graph of fully connected NN, Vector-Jacobian-Product (VJP) vs chainrule and multiplication of Jacobians.
The story of the cat's brain surgery: cortex + convolutional layer and its Vector-Jacobian-Product (VJP)
Where the hell does the loss come from? MAP and ML estimate, KL divergence and losses.
Why is learning prone to fail? - Structural issues: layers + issues, batch-norm, drop-out
Why is learning prone to fail? - Optimization issues: optimization vs learning, KL divergence, SGD, momentum, convergence rate, Adagrad, RMSProp, AdamOptimizer, diminishing/exploding gradient, oscillation, double descent
What can('t) we do with a deep net?: Classification (ResNet, Squeeze and Excitation Nets), Segmentation (DeepLab), Detection (Yolo, fast-RCNN), Regression (OpenPose), Spatial Transformer Nets,
Reinforcement learning: Approximated Q-learning, DQN, DDPG, Derivation of the policy gradient (REINFORCE), A2C, TRPO, PPO, Reward shaping, Inverse RL, Applications,
Memory and attention: recurrent nets, Image transformers with attention module
Generative models: GANs and diffusion models
Implicit layers: Backpropagation through unconstrained and constrained optimization problems, ODE solvers, roots, fixed points) + existing end-to-end differentiable modules cvxpy, gradSLAM, gradMPC, gradODE, pytorch3d
- Syllabus of tutorials:
-
The labs are divided into two parts, in the first one, the students will solve elementary deep ML tasks from scratch (including the reimplementation of autograd backpropagation), in the second one, students will build on existing templates in order to solve complex tasks including RL, tranformers and generative networks.
- Study Objective:
- Study materials:
-
Ian Goodfellow and Yoshua Bengio and Aaron Courville, Deep learning, MIT press, 2016 http://www.deeplearningbook.org
- Note:
- Further information:
- https://cw.fel.cvut.cz/wiki/courses/b3b33urob/start
- Time-table for winter semester 2024/2025:
-
06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon Tue Wed Thu Fri - Time-table for summer semester 2024/2025:
- Time-table is not available yet
- The course is a part of the following study plans:
-
- Cybernetics and Robotics 2016 (compulsory elective course)