Navigation

Seminar Meta Learning

Lecturers

Details

Time and place:

This course will be held online until the coronavirus pandemic is contained to such an extent that the Bavarian state government can allow face-to-face teaching again. Information regarding the online teaching will be provided in the studon course.

  • Mon 8:15-9:45, Room KH 1.021

Fields of study

  • WPF INF-MA from SEM 1
  • WPF MT-MA-BDV from SEM 1
  • WPF CE-MA-TA-MT from SEM 1

Prerequisites / Organizational information

Registration via StudOn:
https://www.studon.fau.de/crs2884557.html

Content

Meta-learning refers to algorithms which aim to learn an aspect of a learning algorithm from data.
Examples of meta-learning methods include algorithms which design neural network architectures based on data, optimize the performance of a learning algorithm or exploit commonalities between tasks to enable learning from few samples on unseen tasks.
These methods hold the promise to automate machine learning even further than learning good representations from data by learning algorithms to learn even better representations.

The seminar will cover the most important works which provide the cornerstone knowledge to understand cutting edge research in the field of meta-learning. Applications will include:
- Learning from few samples
- Automatically tuning neural network architectures
- Determining appropriate equivariances
- Disentangling causal mechanisms

Recommended Literature

Finn et al., "Model-agnostic meta-learning for fast adaptation of deep networks", ICML 2017 Zhou et al., "Meta-learning symmetries by reparameterization", Arxiv Snell et al., "Prototypical networks for few-shot learning", Neurips 2017 Triantafillou et al., "Meta-dataset: A dataset of datasets for learning to learn from few examples", ICLR 2020 Vinyals et al., "Matching networks for one shot learning. ", Neurips 2016 Zoph et al. "Neural Architecture Search with Reinforcement Learning", Journal of Machine Learning Research 20 (2019) Bengio et al., "A meta-transfer objective for learning to disentangle causal mechanisms", ICLR 2020 Santoro et al., "Meta-Learning with Memory-Augmented Neural Networks", ICML 2016 Ravi et al., "Optimization as a model for few-shot learning", ICLR 2016 Munkhdalai et al., "Meta Networks", ICML 2017 Sung et al. "Learning to Compare: Relation Network for Few-Shot Learning", CVPR 2018 Nichol et al. "On First-Order Meta-Learning Algorithms", Arxiv

Additional information

Keywords: algorithms; medical image processing

Expected participants: 10