Advanced Machine Learning for Physics (PhD 2026)

PhD Student's Registration to the course: link

Course Information and Syllabus

Contacts: Stefano Giagu (stefano.giagu [at] uniroma1.it) and Andrea Ciardiello (andrea.ciardiello [at] uniroma1.it)

Program:

General objective of the course is to familiarise with advanced deep learning techniques based on differentiable neural network models with different learning paradigms; to acquire skills in modelling complex problems, through deep learning techniques, and understand how to apply these techniques in different contexts in the fields of physics, basic and applied scientific research.

Topics covered include: recalls of differentiable artificial neural networks and use of the pytorch library for ANN design, learning paradigmas, ANN for visions: segmentation and object detections, generativeAI: autoregressive models, invertible models, diffusion models, uncertainty quantification on ANNs, Graph Neural Networks, Attention and Transformers, Reinforcement Learning, Energy Models, AI explainability, Quantum Machine Learning on near-term quantum devices.

Approximately 50% of the lectures are frontal lessons supplemented by slide projections, aimed at providing advanced knowledge of Deep Learning techniques. The remaining 50% is based on hands-on computational practical experiences that provide some of the application skills necessary to autonomously develop and implement advanced Deep Learning models for solving various problems in physics and scientific research in general.

Indispensable prerequisites: basic concepts in machine learning, python language programming, standard python libraries (numpy, pandas, matplotlib, torch/pytorch )

• a basic python course on YT (many others available on web: https://youtu.be/_uQrJ0TkZlc 

• tutorial on numpy, matplotlib, pandas: https://jakevdp.github.io/PythonDataScienceHandbook/)

• basic concepts of ML:  Introduction + Part I (sec. 5: ML basics) of the book I. Goodfellow et al.: https://www.deeplearningbook.org/

• tutorials on pytorch web site: https://pytorch.org/

• an introductory course on pytorch on YT (many others available on web): https://youtu.be/c36lUUr864M

Depending on the requirements of your specific PhD course each students can decided how may lectures/hands-on to attend to reach the required CFUs:  20h, 40h, 60h (60h corresponds to the entiere course).

Forum group (telegram group):

•  https://t.me/+69bQpfi5j74yM2Zk

Github repository for the course: https://github.com/stefanogiagu/corso_AML_2026

Google meet to attend lectures and exercise sessions:  https://meet.google.com/fbj-fjvu-hqf

Lectures and hands-on can also be followed in person (not mandatory, lectures and hand-on will be streamed and recorded with google meet): 

• lectures: Aula N. Mortara (3), dip. fisica E. Fermi

• hands-on: labSS, laboratorio segnali e sistemi, first floor, dip. fisica G. Marconi

Calendar and detailed program:

• all lectures and lab sessions can be followed remotely on https://meet.google.com/fbj-fjvu-hqf

• folder with lectures' recodings (when available)

References:

• DL: I. Goodfellow, Y. Bengio, A. Courville: Deep Learning, MIT Press (https://www.deeplearningbook.org/)

• PB: P. Baldi, Deep Learning in Science, Cambridge University Press

• DL2: C. Bishop, Deep Learning, Springer

• SCR: S. Scardapane, lice's Adventures in a Differentiable Wonderland, https://arxiv.org/abs/2404.17625 (book: https://www.amazon.it/dp/B0D9QHS5NG)

• GRL: W. L. Hamilton, Graph Representation Learning Book, MCGill Uni press (https://www.cs.mcgill.ca/~wlh/grl_book/files/GRL_Book.pdf)

• SP: M.Schuld, F.Petruccione, Machine Learning with Quantum Computers, Springer

1. L1 - 3.3.2026 (slides) h8:00-10:00

   • course information and synopsis 

   • recalls of artificial neural networks, CNNs, RNNs (DL ch 6 (6.1,6.2,6.3, 6.4, 6.5),  DL2 ch 6,7,8,9,10 , SCR Ch5, 6, 7)

     • artificial neuron model  and MLPs

     • activations functions for hidden and output layers)

     • training of an ANN, regularisation

     • image representation and input properties of a CNN (symmetry, translation invariance, self-similarity, compositionality, locality) and learned convolutional filters (DL ch 9 (9.1,9.2, 9.4))

     • local receptive field, convolution operation, pooling layers

     • Vanilla RNN cell: structure and operating principle (DL ch 10 (intro, 10.2)

     • StackedRNN, Bidirectional RNN, Encoder-Decoder RNN (seq2seq)

     • LSTM: description of operations (note by C.Olahand for details DL ch 10 (10.10))

   • Neural architectures for object detection and segmentation (DL2: 10.4. 10.5)

     • semantic segmentation, downsampling-upsampling (arXiv:1411.4038., arXiv:1505.04366)
       object detection, IoU, anchor boxes, non-max supression

       • region proposals, R-CNN, Fast and Faster R-CNN (arXiv:1311.2524,  arXiv:1506.01497 )

       • Yolo and SSD models (arXiv:1506.02640, arXiv:1512.02325)

2. optional - 9.3.2026 (notebooks) h12:00-15:00

   • implementation in pytorch of an hand-to-hand pipeling to train & test a simple MLP 

3. L2 - 10.3.2026 (slides) h8:00-10:00

   • introduction to HPC and Parallel acceleration for AI, the Leonardo supercomputer (with Sergio Orlandini, Cineca)