BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Cambridge MedAI Seminar Series  - Dr Dimitris Spathis\, Senior Res
 earch Scientist at Nokia Bell Labs and Dr Katharina Zühlsdorff\, Visiting
  Postdoctoral Fellow at Department of Psychology
DTSTART:20240130T120000Z
DTEND:20240130T130000Z
UID:TALK210049@talks.cam.ac.uk
CONTACT:Ines Machado
DESCRIPTION:The *Cancer Research UK Cambridge Centre* and the *Department 
 of Radiology at Addenbrooke's* are pleased to announce a seminar series on
  *Artificial Intelligence (AI) in Medicine*\, which aims to provide a comp
 rehensive overview of the latest developments in this rapidly evolving fie
 ld. As AI continues to revolutionize healthcare\, we believe it is essenti
 al to explore its potential and discuss the challenges and opportunities i
 t presents.\n\nThe seminar series will feature prominent experts in the fi
 eld who will share their research and insights on a range of topics\, incl
 uding AI applications in disease diagnosis\, drug discovery\, and patient 
 care. Each seminar will involve two talks\, followed by an interactive dis
 cussion with a light lunch! We hope that this seminar series will be a val
 uable platform for researchers\, practitioners and students to learn about
  the latest trends and explore collaborations in the exciting field of AI 
 in Medicine.\n\n\nThe next seminar will be held on *30 January 2024\, 12-1
 pm at the Jeffrey Cheah Biomedical Centre (Main Lecture Theatre)\, Univers
 ity of Cambridge* and streamed *online via Zoom*. This month will feature 
 the following two talks:\n\n\n*Multimodal\, data-efficient\, and robust AI
  for real-world biosignals and the role of generative models - Dr Dimitris
  Spathis\, Senior Research Scientist at Nokia Bell Labs and Visiting Resea
 rcher at University of Cambridge*\n\n\nDimitris Spathis is a senior resear
 ch scientist at Nokia Bell Labs and a visiting researcher at the Universit
 y of Cambridge\, where he completed his PhD. His research enables machine 
 learning to handle complex real-world data efficiently\, with a particular
  interest in health sensing. He has previously worked at Microsoft Researc
 h\, Telefonica\, and Ocado. He serves on the program committees of top AI 
 conferences such as AAAI\, IJCAI\, and KDD\, and the editorial board of Na
 ture Digital Medicine. Read more: https://dispathis.com/. \n\n\nAbstract: 
 The limited availability of labels for machine learning on multimodal data
  hampers progress in the field. In this talk\, I will discuss our recent e
 fforts to address this problem\, building on the paradigms of self-supervi
 sed and multimodal learning. With models such as CroSSL\, Step2Heart\, and
  SelfHAR\, we put forward principled ways to learn generalizable represent
 ations from high-resolution data through masking\, knowledge distillation\
 , and physiology-inspired pre-training. We show that these models can be a
 pplied to various clinically relevant applications to improve mental healt
 h\, fitness\, sleep\, and voice-based diagnostics. At the same time\, due 
 to data size limitations\, these models are limited in size and generaliza
 tion capabilities compared to popular generative models such as GPT. What 
 if we could use Large Language Models (LLMs) as data-agnostic pre-trained 
 models? I will close the talk by highlighting where LLMs fail in processin
 g sequential data as text tokens and some ideas on how to address the crit
 ical "modality gap".\n\n\n*Using machine learning methods to improve class
 ification and prediction of psychiatric conditions - Dr Katharina Zühlsdo
 rff\, Visiting Postdoctoral Fellow at Department of Psychology*\n\nKathari
 na Zühlsdorff is a graduate-entry Medicine student and researcher in Cogn
 itive Computational Neuroscience at the University of Cambridge. She is a 
 Foulkes Foundation Fellow (2023 intake) and Downing College Bye-Fellow in 
 Psychology. She completed her PhD at the Department of Psychology\, Univer
 sity of Cambridge and the Alan Turing Institute\, London\, in September 20
 22. She researches the behavioural and neural circuits underlying reinforc
 ement learning in neuropsychiatric disorders such as substance use disorde
 r and depression. Moreover\, she works on the application of deep learning
  algorithms to large-scale\, multimodal datasets to identify patterns that
  may help us understand the aetiology of psychiatric diseases better.\n\nA
 bstract: Cognitive flexibility can be investigated using tests such as pro
 babilistic reversal learning (PRL). In various neuropsychiatric conditions
 \, including substance use disorders\, gambling disorder\, major depressiv
 e disorder and schizophrenia\, overall impairments in PRL flexibility are 
 observed. Using reinforcement learning (RL) models\, a deeper mechanistic 
 explanation of the latent processes underlying flexibility can be gained. 
 I will present results from an analysis of PRL data from individuals with 
 different psychiatric diagnoses using a hierarchical Bayesian RL approach 
 and relate behavioural findings to the underlying neural substrates. Furth
 ermore\, I will discuss how graph neural network models can be used to inc
 orporate cognitive and neuroimaging data to improve prediction of psychiat
 ric conditions.\n\nThis is a *hybrid event* so you can also join via Zoom:
  \n\nhttps://zoom.us/j/99050467573?pwd=UE5OdFdTSFdZeUtIcU1DbXpmdlNGZz09\n\
 nMeeting ID: 990 5046 7573 and Passcode: 617729\n\nWe look forward to your
  participation! If you are interested in getting involved and presenting y
 our work\, please email Ines Machado at im549@cam.ac.uk
LOCATION:Jeffrey Cheah Biomedical Centre (Main Lecture Theatre)\, Universi
 ty of Cambridge
END:VEVENT
END:VCALENDAR