Machine (Deep) Learning for physicists 2024-25 (EUtopia)
Module Convenor: Rudo Roemer (U Warwick) and Mats Granath (U Gothenburg)
- Times: Mondays 16-17 UK/17-18 EU and Wednesdays 16-17 UK/17-18 EU
- 1st (online) lecture: Wednesday, January 8th, 2025
- Course duration: MPAGS + CY Cergy-Paris Universite, 6 weeks lectures, 5 weeks project work
Join Zoom MeetingLink opens in a new window (Meeting ID: 891 4295 5970, Passcode: 307895), Slack discussion roomLink opens in a new window
Lecture slidesLink opens in a new window, MatsGranathLectureNotesLink opens in a new window, CodesLink opens in a new window, Google ColaboratoryLink opens in a new window
The course is for the post-graduate students of the EUtopia Alliance (such as those on the CY Cergy-Paris Universite M2-level Postgraduate course 2024-25) and all interested students of the Midlands Physics Alliance Graduate School.
Machine learning and deep learning are statistical analysis techniques that use strategies of artificial intelligence to characterize complex data and extract deep information. In recent years, these techniques have begun to be used not only in traditional computer science test cases, but also in real world applications as well as, more recently, in areas of advanced physics. In condensed matter systems, such techniques have been shown to give useful insight into Ising and spin ice models [1], low dimensional topological systems [2], strongly correlated systems [3], as well as random two- and three-dimensional topological and non-topological systems [4]. It is probably fair to say that machine and deep learning will become standard statistical analysis tools in the future [5].
In this short course, we want to understand some of the basic principles underlying the recent successes of the DL approach to data analysis. We will do so in a hands-on manner, following up our theoretical understanding with examples using state-of-the-art DL packages such as Keras, FastAI, TensorFlow and PyTorch. In doing so, we will use Jupyter notebooks as frontend to Python. Participants are assumed to have their own DL platform at hand (see here for how I installed mine), although mostly modern laptop resources should be sufficient.
[1] J. Carrasquilla and R. G. Melko: Nature Physics 13 (2017) 431; A. Tanaka and A. Tomiya: Journal of the Physical Society of Japan 86 (2017) 063001.
[2] Y. Zhang and E.-A. Kim: Phys. Rev. Lett. 118 (2017) 216401; P. Zhang, H. Shen, and H. Zhai: arXiv:1708.09401 (2017).
[3] G. Carleo and M. Troyer: Science 355 (2017) 602; P. Broecker, J. Carrasquilla, R. G. Melko, and S. Trebst: Scientific Reports 7 (2017) 8823; K. Ch’ng, J. Carrasquilla, R. G. Melko, and E. Khatami: Phys. Rev. X 7 (2017) 031038; L. Li, T. E. Baker, S. R. White, and K. Burke: Phys. Rev. B 94 (2016) 245129; E. P. van Nieuwenburg, Y.-H. Liu, and S. D. Huber: Nature Physics 13 (2017) 435; L. Huang and L. Wang: Phys. Rev. B 95 (2017) 035105; F. Schindler, N. Regnault, and T. Neupert: Phys. Rev. B 95 (2017) 45134; H. Saito: Journal of the Physical Society of Japan 86 (2017) 093001; H. Saito and M. Kato: arXiv:1709.05468 (2017); H. Fujita, Y. Nakagawa, S. Sugiura, and M. Oshikawa: arXiv:1705.05372 (2017).
[4] T. Ohtsuki and T. Ohtsuki: Journal of the Physical Society of Japan 85 (2016) 123706; T. Ohtsuki and T. Ohtsuki: Journal of the Physical Society of Japan 86 (2017) 044708. N. Yoshioka, Y. Akagi, and H. Katsura: arXiv:1709.05790 (2017)
[5] Machine Learning Physics. in J. Phys. Soc. Jpn., Special Topics (ed. Ohtsuki, T.) (Physical Society of Japan, 2024).
Lecture Recordings
lecture 1Link opens in a new window, lecture 2Link opens in a new window, lecture 3, lecture 4, lecture 5, lecture 6, lecture 7, lecture 8, lecture 9, lecture 10, lecture 11, lecture 12, lecture 13 (all with magic="MLC#1235813)
Further literature
Please have a look at the .bib file that I use for the lecture notes. It contains many more entries than those actually cited in the lecture notes.
Assessments
Upload hereLink opens in a new window before Sunday, March 30th, 2025 at 23:59pm!
| name | place | date received | topic as far as we understand it and can summarize it in one sentence here ;-) | status (email/download/marking/done) |
| Grace Hannaford | Warwick | 14/3/2025 | Image classification of coat colors fastai | passed |
| Rhys Collins | Warwick | 17/3/2025 | Image classification of football stadiums using fastai | passed |
|
Gwon Yueng Chiu |
Warwick | 21/3/2025 | Image classification of road signs using TensorFlow | passed |
|
Benjamin Page |
Warwick | 25/3/2025 | Classification of Rock Paper Scissors using fastai | passed |
|
Jen Feron |
Nottingham | 25/3/2025 | Classification of lego images using fastai | passed |
|
Anna Dalmasso |
Nottingham | 25/3/2025 | Classification of parrots using CNN | passed |
| Alexander Abbey
|
Nottingham | 25/3/2025 | Classification of mushrooms in terms of fastai | passed |
| Ellis Hewins | Nottingham | 25/3/2025 | Study of word2vec model | passed |
| Joseph Whitmore | Nottingham | 25/3/2025 | Classification of video game controllers by tensorflow | passed |
|
Tafadzwa Zivave |
Warwick | 27/3/2025 | Classification of snakes using fastai | passed |
| Christopher Phillips | Warwick | 29/3/2025 | Classification of stars and galaxies using CNN | passed |
| Matt Godfrey | Warwick | 29/3/2025 | Classification of MNIST using TensorFlow | passed |
| Rebecca Meadowcroft | Warwick | 29/3/2025 | Weather prediction using decision tree and random forest | passed |
| Yu Zhong | Warwick | 30/3/2025 | Image classification of stringed instruments using fastai | passed |
| Thomas Gledhill | Warwick | 30/3/2025 | Identify whether images contain parrots or eagles using the BeautifulSoup library | passed |
| Ellie O'Brien |
Sheffield |
27/5/2025 (extension approved) |
Classification of Galapagos islands using CNN | passed |
| BONDO DE YOGOULOU Seth Hilkija |
CYU Cergy Paris |
30/3/2025 |
Predicting the number of deaths following COVID-19 vaccination | passed |
| Edgar BOOH |
Cergy |
30/3/2025 |
Prediction of a car's MPG based on various criteria | passed |
| DEVASAGAYAM Hubert |
Cergy |
30/3/2025 |
Prediction of obesity and overweight | passed |
| FACCHINI Jean |
Cergy |
30/3/2025 |
Prediction of a Ligue 1 match result using Keras/TF | passed |
| FALL El Hadji Abdoulaye |
Cergy |
30/3/2025 |
House price prediction using neural networks | passed |
| HARIKA Nour |
Cergy |
30/3/2025 |
Classification and prediction of the class of the celestrial object (Stars, Galaxy, Quasar) | passed |
| HERVET Roger Stan |
Cergy |
30/3/2025 |
Predict the stock price of SpaceX using Hybrid (with Random forest and Feed forward neural network) | passed |
| HERVY GARCIA Lucien |
Cergy |
30/3/2025 |
Predicting breast cancer | passed |
| MAHERZI Marie-Thérèse |
Cergy |
30/3/2025 |
Classification of Student Depression using Keras | passed |
| MUNARI Maxime |
Cergy |
30/3/2025 |
Image classification of tumors using CNNs | passed |
| OUMAROU Godje Thibaut |
Cergy |
30/3/2025 |
Predicting solar energy production with high accuracy | passed |
New meeting room for Feb 24 at 16:00:
Join here!Link opens in a new window The passcode remains the same.