Course unit, curriculum year 2024–2025
DATA.ML.200
Deep Learning, 5 cr
Tampere University
- Description
- Completion options
Teaching periods
Active in period 2 (21.10.2024–31.12.2024)
Course code
DATA.ML.200Language of instruction
EnglishAcademic years
2024–2025, 2025–2026, 2026–2027Level of study
Advanced studiesGrading scale
General scale, 0-5Persons responsible
Responsible teacher:
Joni KämäräinenResponsible teacher:
Tuomas VirtanenResponsible organisation
Faculty of Information Technology and Communication Sciences 100 %
Coordinating organisation
Computing Sciences Studies 100 %
Ydinsisältö
- Deep neural networks layers: convolutional neural networks, recurrent neural networks, transformers, multilayer perceptrons
- Components of deep neural networks: nonlinearities, normalization, subsampling
- Task-specific loss functions
- Training deep neural networks: stochastic gradient descent, chain rule in gradient calculation, and flow of information
- DNN architectures: encoder-decoder structures, autoencoders, U-nets, handling the depth by residual and skip connections
- Supervised, self-supervised, adversarial learning
- Implementations in Python: Pytorch or Tensorflow
Learning outcomes
Prerequisites
Compulsory prerequisites
Further information
Learning material
Equivalences
Studies that include this course
Completion option 1
Exercises and exam
Completion of all options is required.
Participation in teaching
21.10.2024 – 08.12.2024
Active in period 2 (21.10.2024–31.12.2024)
Exam
11.12.2024 – 11.12.2024
Active in period 2 (21.10.2024–31.12.2024)