Applied Artificial Intelligence

• Engineering Mathematics
• Linear Algebra
• Probability/Statistics
• Introduction to Programming

Introduction to Artificial Intelligence

• Definitions: Artificial Intelligence, Machine Learning, Deep Learning, Data Science
• History and recent developments
• Examples of applications (general and in engineering)

Introduction to classical data analysis:

• Data structures: samples, features, target
• Statistical basics: (co-)variance, correlation, statistical relationship vs. causality
• Cross-validation: training and test datasets, fitting and forecasting
• Supervised learning: regression vs. classification, k-Nearest Neighbors, linear and logistic regression, linear support vector machines, decision trees
• Unsupervised learning: clustering, scaling

Fundamentals of supervised learning using neural networks (NN)

• NN architectures, neuron models and activation functions
• Learning algorithms for feedforward networks including error backpropagation
• Generalization and the bias-variance dilemma

Deep learning architecture including Convolutional Neural Networks (CNN)

• Image classification using CNNs

 Sequence models (Recurrent Neural Networks) for load forecasting

• Basic idea of LSTM
• Basic idea of Transformers

 Basics of Reinforcement Learning

• Explanation of key terms such as state, action, environment, agent, or policy
• Q-learning
• Deep Learning

After successfully completing this course, students will be able to:

• Explain the basic ideas of learning algorithms
• Distinguish between correlation and causation
• Understand, apply, and interpret classical tools like k-Nearest Neighbors, clustering, and decision trees
• Explain network architectures, neuron models, and activation functions
• Describe loss/error functions and the concept of error backpropagation
• Identify application areas of different methods
• Apply standard frameworks such as PyTorch/sklearn for implementing machine learning or data science solutions

• Lectures
• Programming exercises, programming projects
• Coaching

• Written final exam (80%)
• Exercice submissions (20%)

For a positive grade, a minimum of 50% of the possible points must be achieved across all parts of the examination.

--

• Goodfellow, I., Bengio, Y., Courville, A. (2016): Deep Learning. MIT Press. http://www.deeplearningbook.org/
• Guido, Sarah; Müller, Andreas C. (2016): Introduction to Machine Learning with Python: A Guide for Data Scientists. Sebastopol, CA: O’Reilly UK Ltd.

In-person classes. Students will be informed about attendance requirements by the lecturer before the course begins.