Applied Artificial Intelligence

• Engineering Mathematics
• Linear Algebra
• Probability/Statistics

Introduction to the basic learning methods:

• supervised learning (for classification, for regression)
• unsupervised and reinforcement learning

Fundamentals of supervised learning based on neural networks (NN):

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

Deep learning architectures including convolutional NN

Autoencoder with application in anomaly detection

Application project in IoT with annually changing topics

• Students can explain the basic ideas of learning procedures.
• They know the network architectures and neuron models/activation functions.
• They can explain the error/loss functions and the idea of error backpropagation explain.
• They can explain the problem of network complexity in terms of generalization and the bias-variance dilemma and apply the standard methods for network regularization.
• They can perform network training using standard frameworks such as PyTorch/Tensorflow.

Lecture and project work

Project evaluation and written final examination.

--

• Zhang, A. Lipton, Z.C., Li, M., Smola, A.J. (2022): Dive into Deep Learning. https://d2l.ai/
• Goodfellow, I., Bengio, Y., Courville, A. (2016): Deep Learning. MIT Press. http://www.deeplearningbook.org/
• Hope, T., Resheff, Y.S., Lieder, I. (2017): Learning TensorFlow. A Guide to Building Deep Learning Systems. O'Reilly

Face-to-face instruction