OxfordXML
Promoting a cross-disciplinary machine learning community to share, learn and connect
OxfordXML brings together researchers across different disciplines to share and learn about the impact of machine learning in their respective fields, such as physics, finance, social sciences, engineering, healthcare, and psychology.
“What we want is a machine that can learn from experience”
Alan Turing
Alan Turing
our mission
To provide a cross-disciplinary platform for Machine Learning researchers to share, learn and connect with other researchers across different disciplines
our community
We bring together researchers from various disciplines to build a community that promotes knowledge transfer, networking and interdisciplinary collaboration.
our activities
Termtime hybrid talks, held at Wolfson College and online, discussing different applications of Machine Learning in an informal and supportive setting.
our audience
We welcome anyone interested in learning more about Machine Learning applications across different fields. Past attendees of our events include postgraduate students, early career researchers and professors.

upcoming events

what's coming up

To receive notifications, please join our mailing list.

Jesus

13

Mar

2024
Citizen Weather Data and Machine Learning to identify urban climate risk at high spatio-temporal resolution

Speaker: Prof Jesus Lizana
Calendar Icon Time: 17:00-18:00
Location Icon Levett Room, Wolfson College & Online (Teams link)

Jesus Lizana is Associate Professor in Engineering Science at the University of Oxford, with a unique experience profile in architecture and engineering. His research focuses on the cross-disciplinary challenges to support the transition towards zero carbon climate-responsive buildings. At Oxford, Lizana is engaged in many research initiatives and has received several prestigious and extensive grants, including a Marie Curie Fellowship. He leads the research on Zero-Carbon Space Heating and Cooling at ZERO Institute and supports the interdisciplinary research in the Future of Cooling Programme of the Oxford Martin School. Alongside his academic career, Lizana also serves as a consultant on many building energy-related projects, data science, and sustainable cooling across various global locations, including the United Kingdom, India, Spain, Morocco, and Saudi Arabia. Lizana received his PhD in low-carbon buildings at the University of Seville in Spain after completing a BSc in Architecture and an MSc in Building Engineering. Previously to his appointment at Oxford, he has lectured and conducted research at the University of Seville (Spain), the University of Edinburgh (Scotland), the Technical University of Munich (Germany), Universidade de Lisboa (Portugal), and the Spanish National Research Council (Spain).

The rapid increase of global mean temperature and unprecedented heat events require new approaches to support and monitor the climate adaptation and heat resilience of cities. Crafting effective plans necessitates accurate data and tools that adapt to the ever-changing dynamics of urban environments. This presentation will show the recent advances in diagnosing and treating accurately, city by city, overheated urban areas (in time and space) where climate adaptation should be prioritised to promote heat resilience. The research aims to fully integrate crowdsourced urban climate observations (citizen weather stations) with satellite and remote sensing data using machine learning techniques to generate high spatio-temporal resolution observations of urban atmospheric states and dynamics. The results will support the development of an urban heat diagnosis tool with global applicability to enable insight and evidence-supported actions to promote zero-carbon and sustainable cooling at different scales. This research is part of the Future of Cooling Programme of the Oxford Martin School.

Speaker

21

Mar

2024
Resurrecting Recurrent Neural Networks for Language Modelling

Speaker: Razvan Pascanu
Calendar Icon Time: 17:00-18:00
Location Icon Buttery, Wolfson College & Online (Teams link)

I'm currently a Research Scientist at DeepMind. I grew up in Romania and studied computer science and electrical engineering for my undergrads in Germany. I got my MSc from Jacobs University, Bremen in 2009. I hold a PhD from University of Montreal (2014), which I did under the supervision of prof. Yoshua Bengio. I was involved in developing Theano and helped writing some of the deep learning tutorials for Theano. I've published several papers on topics surrounding deep learning and deep reinforcement learning (see my scholar page). I'm one of the organizers of EEML (www.eeml.eu) and part of the organizers of AIRomania. As part of the AIRomania community, I have organized RomanianAIDays since 2020, and helped build a course on AI aimed at high school students.

In this talk I will focus on State Space Models (SSMs) , a subclass of Recurrent Neural Networks (RNNs) that has recently gained some attention through works like Mamba, obtaining strong performance against transformer baselines. I will start by first explaining how SSMs can be viewed as just a particular parametrization of RNNs and what are the crucial differences compared to previous recurrent architectures that led to these results. My goal is to demystify the relative complex parametrization of the architecture and identify what elements are needed for the model to perform well. In this process I will introduce the Linear Recurrent Unit (LRU), a simplified linear layer inspired by existing SSM layers. In the second part of the talk, I will focus on language modelling and the block structure in which such layers tend to be embedded. I will argue that beyond the recurrent layer itself, the block structure borrowed from transformers plays a crucial role in the recent successes of this architecture, and present results at scale of well performing hybrid recurrent architectures as compared to strong transformer baseline. I will close the talk with a few open questions and thoughts on the importance of recurrence in modern deep learning models.

Past events (2022/2023)
Events held and scheduled by us
7
Mar 2024
MULTI-AGENT REINFORCEMENT LEARNING
Jakob Foerster
Recording of the seminar can be viewed to come.
  • Wolfson College
    05:00 PM - 06:00 PM
  • Wolfson College
    Wolfson College
6
Mar 2024
LINKING DISCIPLINES, OMICS AND AI TO IMPROVE HUMAN HEALTH
Prof James Crabbe
Recording of the seminar can be viewed to come.
  • Wolfson College
    01:00 PM - 02:00 PM
  • Wolfson College
    Wolfson College
27
Feb 2024
ARTIFICIAL INTELLIGENCE FOR MATHEMATICAL DISCOVERY
Daattavya Aggarwal
Recording of the seminar can be viewed to come.
  • Wolfson College
    05:00 PM - 06:00 PM
  • Wolfson College
    Wolfson College
19
Feb 2024
USER PROFILING FOR PERSONALIZATION
Dr Huizhi Liang
Recording of the seminar can be viewed to come.
  • Wolfson College
    01:00 PM - 02:00 PM
  • Wolfson College
    Wolfson College
15
Feb 2024
SEEING THE UNSEEN: MACHINE LEARNING IN CARDIAC ELECTROPHYSIOLOGY
Dr Rasheda Chowdhury
Recording of the seminar can be viewed to come.
  • Wolfson College
    01:00 PM - 02:00 PM
  • Wolfson College
    Wolfson College
8
Feb 2024
RISKS AND BENEFITS OF OPEN SOURCING LANGUAGE MODELS
Jakob Foerster, Christian Schroeder, Aleksandar Petrov,
Francisco Girbal, Fazl Barez, Joshua Loo
Recording of the seminar can be viewed to come.
  • Wolfson College
    05:00 PM - 07:00 PM
  • Wolfson College
    Engineering Science Department, Thom Building
31
Jan 2024
Multi-Agent Security
Christian Schroeder
Recording of the seminar can be viewed to come.
  • Wolfson College
    05:00 PM - 06:00 PM
  • Wolfson College
    Wolfson College
17
Jan 2024
MORAL UNCERTAINTY IN AUTONOMOUS AGENTS
Jázon Szabó
Recording of the seminar can be viewed to come.
  • Wolfson College
    06:00 PM - 07:00 PM
  • Wolfson College
    Wolfson College
06
Dec 2023
Physics-informed generative networks
Dr Fabio Pizzati
Recording of the seminar can be viewed to come.
  • Wolfson College
    01:00 PM - 02:30 PM
  • Wolfson College
    Wolfson College
30
Nov 2023
Bridging Millennia: Machine Learning's Impact on Assyriology
Ms Émilie Pagé-Perron
Recording of the seminar can be viewed to come.
  • Wolfson College
    01:00 PM - 02:30 PM
  • Wolfson College
    Wolfson College
23
Nov 2023
Embeddings for Knowledge Graphs and Multimodal Representations
Dr Nitisha Jain
Recording of the seminar can be viewed to come.
  • 01:00 PM - 02:30 PM
  • Wolfson College
    Wolfson College
25
Oct 2023
Some applications of AI in Mathematics and Theoretical Physics
Dr Andrei Constantin
Recording of the seminar can be viewed to come.
  • 01:00 PM - 02:30 PM
  • Wolfson College
13
Jun 2023
Personalised Treatment for Mental Health
Dr Qiang Liu
Recording of the seminar can be viewed to come.
  • 02:00 PM - 03:30 PM
  • Wolfson College
2
Jun 2023
INNOVATING IN MEDICAL DEVICE DEVELOPMENT
Dr Miguel Xochicale
Recording of the seminar can be viewed to come.
  • 02:30 PM - 04:00 PM
  • Wolfson College
26
May 2023
Towards Safe & Robust AI for Image-Guided Diagnosis and Intervention
Dr Mobarakol Islam
Recording of the seminar can be viewed to come.
  • 02:30 PM - 04:00 PM
  • Wolfson College
19
May 2023
Feature Attribution for Neural Network Explanation & Diversified Dynamic Routing for Vision Tasks
Csaba Botos & Ashkan Khakzar
Recording of the seminar can be viewed here.
  • 02:30 PM - 04:00 PM
  • Wolfson College
13
Mar 2023
Intelligence, artificial or not: conversations between developmental neuroscience and AI
Dr. Martin Frasch
Recording of the seminar can be viewed here.
More information: FraschLab.org
  • 02:30 PM - 04:00 PM
  • Wolfson College
21
Feb 2023
How Do Language Models Like ChatGPT Process Complex Words?
Mr. Valentin Hofmann
Recording of the seminar can be viewed here.
  • 02:30 PM - 04:00 PM
  • Wolfson College
9
Feb 2023
Advances in Sentiment Analysis of the Large Mass-Media Documents
Dr. Nicolay Rusnachenko
To download the presentation slides: click here.
  • 02:30 PM - 04:00 PM
  • Wolfson College
19
Jan 2023
An Arms Race in Intellectual Property Protection of Deep Learning Models
Dr Youcheng Sun
  • 02:30 PM - 04:00 PM
  • Wolfson College
12
Jan 2023
GENERATING PATIENT RECORDS USING DIFFUSION MODELS
Dr Taha Ceritli
  • 02:30 PM - 04:00 PM
  • Wolfson College
12
Dec 2022
LEVERAGING MACHINE LEARNING TO IDENTIFY BLOOD CANCER TYPES
Ms Helen Theissen
  • 02:30 PM - 04:00 PM
  • Wolfson College
21
Jun 2022
Application of deep learning in fetal heart rate monitoring
Dr Daniel Asfaw
  • 03:30 PM - 05:00 PM
  • Florey Room, Wolfson College
30
jun 2022
Deep learning strategies for ultrasound in pregnancy
Dr Yi Yin
  • 1:00 PM - 2:30 PM
  • Florey Room, Wolfson College
15
jul 2022
Predicting activity patterns of regulatory elements in zebrafish using ML
Ms Andrea Rodriguez Delherbe
  • 3:00 PM - 4:30 PM
26
jul 2022
Agent-based modelling of accent retraction in Balto-Slavic
Mr Toby Hudson
  • 4:00 PM - 5:30 PM
About Us
A vision for an open, cross-disciplinary machine learning network
Founded in 2019 by Dr Stephen Suryasentana (now at University of Strathclyde) and Dr Yaling Hsiao (now at Birmingham University), OxfordXML (where XML stands for Cross-disciplinary Machine Learning) is a research cluster based in Wolfson College that aims to provide a cross-disciplinary platform for researchers across different disciplines to come and share their experience on how machine learning or artificial intelligence has impacted on their research. Furthermore, it hopes to provide an open community for researchers across different departments to connect and initiate interdisciplinary collaboration.
Committee
  • Prof Antoniya Georgieva (cluster head)
  • Dr Yi Yin (lead organiser)
  • Mr Csaba Botos (student organiser)
To join our mailing list: CLICK HERE
Contact us below if you are interested in speaking at our events