General
The information in Oodi is outdated. The correct information is here.
Teaching arrangement changes caused by the Coronavirus
- The lectures are arranged over zoom. Links to the zoom meetings can be found on this page.
- The exercise sessions are held remotely. Please find instructions on this page.
- The office hours sessions have been canceled. You can contact the lecturer in slack or by email.
Course description
- Contents: Machine learning with deep neural networks. Programming using PyTorch.
- Assessment: returned assignments (no project work and no exam).
- Prerequisites:
- good level of programming in Python
- linear algebra:
- vectors, matrices, eigenvalues and eigenvectors
- vectors, matrices, eigenvalues and eigenvectors
- basics of probability and statistics:
- sum, product rule, Bayes' rule
- expectation, mean, variance, median
- maximum likelihood, Kullback-Leibler divergence
- sum, product rule, Bayes' rule
- basics of machine learning (recommended):
- supervised and unsupervised learning
- overfitting and underfitting
- regularization
- Course contents:
- Introduction to deep learning
- Optimization methods
- Regularization methods
- Convolutional neural networks
- Recurrent neural networks
- Attention-based models
- Graph neural networks
- Deep learning with few labeled examples
- Deep autoencoders
- Flow-based and autoregressive generative models
- Generative adversarial networks
- Course slack: deeplearn2020-aalto.slack.com
After the course, the student understands the basic principles of deep learning: multi-layer perceptrons, convolutional and recurrent neural networks; stochastic gradient descent and backpropagation; means to prevent overfitting. The student understands how to do supervised learning (classification and regression) and unsupervised learning with neural networks. The student knows modern neural architectures used for image classification, time series modeling and natural language processing. The student has experience on training deep learning models in PyTorch.