Advanced Transfer Learning with Deep Neural Networks
The course covers the following topics:
Introduction: why deep learning with multiple tasks matters
Transfer learning via fine-tuning and domain adaptation
Multi-task learning
- with fixed neural network architectures
- with task-aware modulation
Meta-learning for few-shot classification and regression - Black-box meta-learning methods
- Optimization-based meta-learning methods
- Non-parametric methods for few-shot learning
Advanced topics - The problem of memorization in meta-learning
- Meta-learning without tasks provided: how to construct training tasks automatically
- Life-long learning: how to learn continuously from a sequence of tasks
Open Challenges in multi-task and meta learning
Level:
Graduate level
Application code:
R3110
Entry requirements:
Basic eligibility for education at the postgraduate level (third-cycle) as well as 7,5 credits within machine learning.
Selection rules:
Restricted admission
Start week:
week: 38
Number of gatherings:
0
Instructional time:
Various times
Tuition fee:
Language of instruction:
Teaching is in English.
Level:
Graduate level
Application code:
R3010
Entry requirements:
Basic eligibility for education at the postgraduate level (third-cycle) as well as 7,5 credits within machine learning.
Selection rules:
Restricted admission
Start week:
week: 03
Number of gatherings:
0
Instructional time:
Various times
Tuition fee:
Language of instruction:
Teaching is in English.
