Robot Learning Course

Welcome to B3B33UROB

This course introduces fundamental and advanced concepts in machine learning with a focus on robotics applications. You’ll learn how robots can learn from data to perform complex tasks, from basic classification and regression to deep neural networks and reinforcement learning.

Course Overview

Robot Learning bridges the gap between traditional robotics and modern machine learning techniques. In this course, you will:

  • Master the fundamentals of supervised learning (classification and regression)
  • Understand how neural networks work from the ground up
  • Learn to train models using gradient descent and backpropagation
  • Explore convolutional neural networks for vision tasks
  • Dive into reinforcement learning for robot control
  • Apply these techniques to real robotics problems

Course Structure

The course content is organized into the following main sections:

📚 Fundamentals

Start here to understand the basic building blocks of machine learning:

  • Datasets and Features
  • Classification and Regression
  • Evaluation Metrics

🤖 Models

Explore different types of machine learning models:

  • k-Nearest Neighbors
  • Linear Classifiers
  • Neural Networks (MLPs)
  • Convolutional Networks

🎯 Training

Learn how models learn from data:

  • Loss Functions
  • Gradient Descent
  • Backpropagation

Prerequisites

  • Linear Algebra (matrix operations, vector spaces)
  • Calculus (derivatives, chain rule)
  • Basic Programming (Python recommended)
  • Probability and Statistics (basic concepts)

Learning Outcomes

By the end of this course, you will be able to:

  1. Understand the mathematical foundations of machine learning
  2. Implement basic learning algorithms from scratch
  3. Train neural networks for various tasks
  4. Apply machine learning to robotics problems
  5. Evaluate model performance and debug training issues
  6. Design appropriate models for specific applications

Getting Started

  1. Begin with the Fundamentals section to build a solid foundation
  2. Work through the examples and exercises in each section
  3. Implement the algorithms to reinforce your understanding
  4. Apply the concepts to the course assignments

Resources

  • Course Materials: Available through CourseWare
  • Assignments: Submit through BRUTE
  • Code Repository: GitHub

Department of Cybernetics, Faculty of Electrical Engineering

Czech Technical University in Prague