Seminar Meta Learning (SemMeL) /CourseID:1867

These resources are password protected!

The password will be provided by lecturer

Detailed information

Keywords: meta learning

Most recent entry on 2021-01-18 

Organisational Unit

Friedrich-Alexander-Universität Erlangen-Nürnberg

Recording type

Themenvorträge

Via

Free / IdM-login / Passwort / Studon

Language

English

Prerequisites / Organisational information
Registration via StudOn: https://www.studon.fau.de/crs3330572.html

 

Contents
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

Associated Clips

Episode
Title
Lecturer
Updated
Via
Duration
Media
1
Seminar Meta Learning (SemMeL) - Good Scientific Presentations
Prof. Dr. Andreas Maier
2020-11-02
IdM-login / Passwort
00:55:06
2
Seminar Meta Learning (SemMeL) - Arka Nandi - Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Prof. Dr. Andreas Maier
2020-11-16
Free
00:40:05
3
Seminar Meta Learning (SemMeL) - Benjamin Geissler - Meta-learning symmetries by reparameterization
Prof. Dr. Andreas Maier
2020-11-30
IdM-login
00:39:57
4
Seminar Meta Learning (SemMeL) - Jonas Utz - Prototypical Networks for Few-shot Learning
Prof. Dr. Andreas Maier
2020-11-23
Free
00:33:52
5
Seminar Meta Learning (SemMeL) - Nicolas Krieg - Meta Dataset - A Dataset of Datasets for Meta Learning
Prof. Dr. Andreas Maier
2020-11-30
IdM-login
00:35:29
6
Seminar Meta Learning (SemMeL) - Juilee Kulkarni - Meta Dataset - Matching networks for one shot learning
Prof. Dr. Andreas Maier
2020-12-08
IdM-login / Studon
00:35:18
7
Seminar Meta Learning (SemMeL) - Anil Bora Yayak - Neural Architecture Search with Reinforcement Learning
Prof. Dr. Andreas Maier
2020-12-14
Free
00:27:27
8
Seminar Meta Learning (SemMeL) - Lena Eichermüller - A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Prof. Dr. Andreas Maier
2020-12-25
IdM-login
00:35:52
9
Seminar Meta Learning (SemMeL) - Nupur Patel - Meta-Learning with Memory-Augmented Neural Networks
Prof. Dr. Andreas Maier
2021-01-13
IdM-login / Passwort
00:34:58
10
Seminar Meta Learning (SemMeL) - Jingwei Song - Optimization as a Model for Few-Shot Learning
Prof. Dr. Andreas Maier
2021-01-18
Free
00:20:48

More courses from Prof. Dr. Andreas Maier

Maier, Andreas
Prof. Dr. Andreas Maier
lecture
2017-01-20
Studon
Maier, Andreas
Prof. Dr. Andreas Maier
lecture
2015-07-16
Free
Schloss1
Prof. Dr. Andreas Maier
lecture
2020-10-13
IdM-login
Schloss1
Prof. Dr. Andreas Maier
lecture
2020-12-23
Free
Maier, Andreas
Prof. Dr. Andreas Maier
lecture
2020-07-12
Free / IdM-login