Entry requirements

120 credits in science/engineering with Introduction to Scientific Computing and Linear Algebra II. Participation in Quantum Physics/Quantum Physics F and Scientific Computing for Data Analysis. Proficiency in English equivalent to the Swedish upper secondary course English 6.

Learning outcomes

On completion of the course, the student should be able to:

• summarize the concepts of deep learning
• apply deep learning to typical problems in physics and engineering
• design and optimize network architectures for different problems in physics and engineering
• verify results from deep learning models with experimental data

Content

Fundamentals of Deep Learning. Generalization, Regularization and Validation, Optimization and Hyperparameter Tuning, Convolutional Neutral Networks, Recurrent Neural Networks, Graph Neural Networks. Classification and Regression Tasks. Visualization & Advanced Computer Vision Methods. Autoencoders. Generative models, variational autoencoders, generative adversarial networks. Applications in physics and engineering, for example, image recognition, analysis of time series data, pulse shape discrimination, real-time low-power on-device computing (IoT applications); Practical skills of using the TensorFlow framework via the high-level Keras python interface; Methods to verify neural network predictions, e.g., through independent experimental data that is obtained in a lab assignment.

Instruction

Lectures, exercise classes and laboratory.

Assessment

Hand-in problems.

If there are special reasons for doing so, an examiner may make an exception from the method of assessment indicated and allow a student to be assessed by another method. An example of special reasons might be a certificate regarding special pedagogical support from the disability coordinator of the university.