Section outline
-
The module covers some recent and interesting development and research topics in the field of machine learning. Topics choice is likely to vary at each edition. Example topics include: deep learning for graphs, continual learning, distributed learning, learning-reasoning integration, edgeAI, lerning beyond backpropagation, neural networks inspired by dynamical systems, ... The module concludes with a final lecture which discusses the course content retrospectively and details the exam modalities, topics and deadlines.
Date Topic References (OLD) References (NEW) Additional Material 28 02/05/2024
(14-16)Fundamentals of deep learning for graphs I
learning with structured data, learning tasks on graphs, message-passing architectures, survey of foundational models for graphs[CHB] Chapter 13
[SP] Chapter 13Software
- PyDGN: our in-house DLG library
- PyTorch geometric
- Deep graph library
Additional readings
[55-56] Seminal works on neural networks for graphs
[57] Recent tutorial paper29 07/05/2024
(11-13)Reservoir Computing
Guest lecture by Andrea Ceni
The content of this lecture is not part of the exam topics30 08/05/2024
(16-18)Alternatives to backpropagation training of (deep) neural models
Guest lecture by Andrea Cossu
The content of this lecture is not part of the exam topics31 14/05/2024
(11-13)Fundamentals of deep learning for graphs II
graph convolutional networks, graph pooling, generative learning on graphs, probabilistic graph models, non-dissipative graph message passing, neural algorithmic reasoning[CHB] Chapter 13
[SP] Chapter 13Additional readings
[58] A work on generalizing pooling to graphs
[59] Probabilistic learning on graphs
[60] Non-dissipative message passing via neural graph ODEs
[61] Survey on deep learning for dynamic graphs
[62] Neural algorithmic reasoning following duality structure in optimization problems32 15/05/2024
(16-18)Beyond accuracy: auditing LLMs based on exams designed for humans
Guest lecture by Wagner Meira Jr
The content of this lecture is not part of the exam topics33 16/05/2024
(14-16)(Deep) Reinforcement Learning fundamentals [SP] Sections 19.1-19.3.1, 19.4, 19.5 (no derivation of policy gradient) Additional readings
[63] Original Q-Learning algorithm
[64] Original DQN paper
[65] Learning with the actor-critic architecture
[66] A masterpiece paper deriving trust-region policy optimization (technical by worth the read)34 21/05/2024
(11-13)
RECOVERY LECTURE - ROOM CAn introduction to causality and causal learning
Guest lecture by Riccardo Massidda35 22/05/2024
(16-18)
RECOVERY LECTURE - ROOM C1Final lecture