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 13
     Software
    - 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 paper
    29
    07/05/2024
    (11-13)
    Reservoir Computing
    Guest lecture by Andrea Ceni

    The content of this lecture is not part of the exam topics

      
    30
    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 topics
        
    31 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 13
    Additional 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 problems
    32 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 topics
        
    33
    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 C
    An introduction to causality and causal learning
    Guest lecture by Riccardo Massidda
        
    35 22/05/2024
    (16-18)
    RECOVERY LECTURE - ROOM C1

     Final lecture