Mon 04 Jul 17:00: The Problem of Size Generalization in Graph Neural Networks
In the past few years, graph neural networks (GNNs) have become the de facto model of choice for graph classification and other tasks on graph structured data. While, from the theoretical viewpoint, most GNNs can operate on graphs of any size, it is empirically observed that their classification performance degrades when they are applied on graphs with sizes that differ from those in the training data. In this talk we will give an overview of the current approaches to tackle the issue of poor size-generalization in GNNs, and we will introduce our recent work in this area.
- Speaker: Davide Buffelli , Universita' di Padova
- Monday 04 July 2022, 17:00-18:00
- Venue: Lecture theatre and zoom (https://cl-cam-ac-uk.zoom.us/j/96155557207?pwd=VXlyUVZidVRxWFRaWS9tak1SUjV3Zz09 ID: 961 5555 7207 Passcode: 913748).
- Series: Artificial Intelligence Research Group Talks (Computer Laboratory); organiser: Pietro Lio.
Mon 15 May 19:30: Optics and biomechanics of the developing and ageing eye - TBC
Abstract not available
- Speaker: Prof. Barbara Pierscionek, Medical Technology Research Centre, Anglia Ruskin University
- Monday 15 May 2023, 19:30-21:00
- Venue: Location: Wolfson Lecture Theatre, Churchill College, and Zoom.
- Series: Cambridge Society for the Application of Research (CSAR); organiser: John Cook.
Mon 06 Feb 19:30: Applications of advanced Raman spectroscopy - TBC
Abstract not available
- Speaker: Prof. Pavel Matousek, Central Laser Facility, RAL, Harwell, UK.
- Monday 06 February 2023, 19:30-21:00
- Venue: Location: Wolfson Lecture Theatre, Churchill College, and Zoom.
- Series: Cambridge Society for the Application of Research (CSAR); organiser: John Cook.
Mon 23 Jan 19:30: Synthetic biology - TBC
Abstract not available
- Speaker: Prof. Tom Ellis, Department of Bioengineering, Imperial College London
- Monday 23 January 2023, 19:30-21:00
- Venue: Location: Wolfson Lecture Theatre, Churchill College, and Zoom.
- Series: Cambridge Society for the Application of Research (CSAR); organiser: John Cook.
Mon 14 Nov 19:30: Developments in hydrogen-electric aviation - TBC
Abstract not available
- Speaker: To be confirmed: Zeroavia
- Monday 14 November 2022, 19:30-21:00
- Venue: Location: Wolfson Lecture Theatre, Churchill College, and Zoom.
- Series: Cambridge Society for the Application of Research (CSAR); organiser: John Cook.
Mon 31 Oct 19:30: Dyslexia, Rhythm, Language and the Developing Brain
Abstract not available
- Speaker: Prof. Usha Goswami, Department of Psychology, University of Cambridge
- Monday 31 October 2022, 19:30-21:00
- Venue: Location: Wolfson Lecture Theatre, Churchill College, and Zoom.
- Series: Cambridge Society for the Application of Research (CSAR); organiser: John Cook.
Mon 17 Oct 19:30: CSAR lecture - Antimicrobial resistance (TBC)
Abstract not available
- Speaker: Prof. Steve Baker, Cambridge Inst. for Therapeutic Immunology & Infectious Disease
- Monday 17 October 2022, 19:30-21:00
- Venue: Location: Wolfson Lecture Theatre, Churchill College, and Zoom.
- Series: Cambridge Society for the Application of Research (CSAR); organiser: John Cook.
Mon 11 Jul 14:00: Combining multi-omics and biological knowledge to extract disease mechanisms Please contact Ciara for further details
Multi-omics technologies, and in particular those with single-cell and spatial resolution, provide unique opportunities to study deregulation of intra- and inter-cellular processes in cancer and other diseases. In this talk I will present recent methods and applications from our group towards this aim, with a focus is on computational approaches that combine data with biological knowledge within statistical and machine learning methods. This combination allows us to increase both the statistical power of our approaches and the mechanistic interpretability of the results. I will also discuss the value to perform perturbation studies, combined with mathematical modeling, to increase our understanding and therapeutic opportunities. Finally, I will show how, using novel microfluidics-based technologies, this approach can also be applied directly to biopsies, allowing to build mechanistic models for individual cancer patients, and use these models to propose new therapies.
Please contact Ciara for further details
- Speaker: Julio Saez-Rodriguez, Faculty of Medicine of Heidelberg University, Director of the Institute of Computational Biomedicine and Group Leader at the EMBL- Heidelberg University Molecular Medicine Partnership Unit (MMPU)
- Monday 11 July 2022, 14:00-15:00
- Venue: CRUK CI Lecture Theatre.
- Series: Seminars on Quantitative Biology @ CRUK Cambridge Institute ; organiser: Ciara.Adeniyi-Jones.
Fri 25 Nov 16:00: How Salmonella reprogrammes a host kinase to drive macrophage polarisation Dr Teresa Thurston, Imperial College London. Hosted by Professor Felix Randow
Abstract not available
Dr Teresa Thurston, Imperial College London. Hosted by Professor Felix Randow
- Speaker: Dr Teresa Thurston, Imperial College London. Hosted by Professor Felix Randow
- Friday 25 November 2022, 16:00-17:00
- Venue: Hybrid meeting, Jeffrey Cheah Biomedical Centre Lecture Theatre and Via Zoom, for more details go to https://www.immunology.cam.ac.uk/.
- Series: Immunology and Medicine Seminars; organiser: Nadine Hirst.
Fri 07 Oct 16:00: Cell death and decision making in macrophages during inflammation Associate Professor Jelena Bezbradica Mirkovic, Kennedy Institute, Oxford. Hosted by Professor Felix Randow
Abstract not available
Associate Professor Jelena Bezbradica Mirkovic, Kennedy Institute, Oxford. Hosted by Professor Felix Randow
- Speaker: Associate Professor Jelena Bezbradica Mirkovic, Kennedy Institute, Oxford. Hosted by Professor Felix Randow
- Friday 07 October 2022, 16:00-17:00
- Venue: Hybrid meeting, Jeffrey Cheah Biomedical Centre Lecture Theatre and Via Zoom, for more details go to https://www.immunology.cam.ac.uk/.
- Series: Immunology and Medicine Seminars; organiser: Nadine Hirst.
Thu 07 Jul 16:00: Mycobacterium tuberculosis genome economization for pathogenesis: “More from less for more” Room changed - will be Seminar Rooms 2/3, Pathology Block, Department of Veterinary Medicine.
Abstract: Mycobacterium tuberculosis (M.tb) is the deadliest bacterial pathogen known to humanity causing the disease TB, taking the largest toll of human lives globally with a person dying every 15-20 seconds despite the fact that TB is completely curable if diagnosed timely and treated properly. This problem is further compounded by the development of drug resistance, to the extent of total drug resistance, HIV AIDS co-infection and the accompanying TB-IRIS and the impending impact of the emerging diabetes epidemic and of late the COVID -19 pandemic. M.tb has undergone reductive evolution, over millions of years, into a very slim and trim genomic and functional architecture. Not only has it shed much of its genome, but has balanced this genome deficit by resorting to very intelligent survival strategies such as gene co option, moon lighting and molecular mimicry.
Room changed - will be Seminar Rooms 2/3, Pathology Block, Department of Veterinary Medicine.
- Speaker: Prof Seyed E. Hasnain, Indian Institute of Technology, Delhi and Sharda University, Greater Noida
- Thursday 07 July 2022, 16:00-17:00
- Venue: Venue to be confirmed.
- Series: Departmental Seminar Programme, Department of Veterinary Medicine; organiser: Fiona Roby.
Fri 08 Jul 11:00: Synthetics with Digital Humans
Abstract
Nowadays, collecting the right dataset for machine learning is often more challenging than choosing the model. We address this with photorealistic synthetic training data – labelled images of humans made using computer graphics. With synthetics we can generate clean labels without annotation noise or error, produce labels otherwise impossible to annotate by hand, and easily control variation and diversity in our datasets. I will show you how synthetics underpins our work on understanding humans, including how it enables fast and accurate 3D face reconstruction, in the wild.
Bio
Dr. Erroll Wood is a Staff Software Engineer at Google, working on Digital Humans. Previously, he was a member of Microsoft’s Mixed Reality AI Lab, where he worked on hand tracking for HoloLens 2, avatars for Microsoft Mesh, synthetic data for face tracking, and Holoportation. He did his PhD at the University of Cambridge, working on gaze estimation.
- Speaker: Dr. Erroll Wood (Staff Software Engineer at Google)
- Friday 08 July 2022, 11:00-12:00
- Venue: https://zoom.us/j/6492509351?pwd=U0hoSzJ0anlhRGhzYVFmTzltNk9wZz09 (meeting ID: 649 250 9351 / passcode: 7mu5ZJ).
- Series: CUED Computer Vision Research Seminars; organiser: Gwangbin Bae.
Wed 06 Jul 11:00: The unreasonable effectiveness of mathematics in large scale deep learning
Recently, the theory of infinite-width neural networks led to the first technology, muTransfer, for tuning enormous neural networks that are too expensive to train more than once. For example, this allowed us to tune the 6.7 billion parameter version of GPT -3 using only 7% of its pretraining compute budget, and with some asterisks, we get a performance comparable to the original GPT -3 model with twice the parameter count. In this talk, I will explain the core insight behind this theory. In fact, this is an instance of what I call the Optimal Scaling Thesis, which connects infinite-size limits for general notions of “size” to the optimal design of large models in practice, illustrating a way for theory to reliably guide the future of AI. I’ll end with several concrete key mathematical research questions whose resolutions will have incredible impact on how practitioners scale up their NNs.
There’s no required reading for the talk but folks can look at my homepage for an overview of Tensor Programs.
- Speaker: Greg Yang, Microsoft Research
- Wednesday 06 July 2022, 11:00-12:30
- Venue: Cambridge University Engineering Department, CBL Seminar room BE4-38.
- Series: Machine Learning Reading Group @ CUED; organiser: James Allingham.
Understanding the development, evolution, and function of bullseye pigmentation patterns in Hibiscus trionum
Thu 30 Jun 14:00: A Comparative Study on the Loss Functions for Image Enhancement Networks
Image enhancement and image retouching processes are often dominated by global (shift-invariant) change of colour and tones. Most “deep learning” based methods proposed for image enhancement are trained to enforce similarity in pixel values and/or in the high-level feature space. We hypothesise that for tasks, such as image enhancement and retouching, which involve a significant shift in colour statistics, training the model to restore the overall colour distribution can be of vital importance. To address this, we study the effect of a Histogram Matching loss function on a state-of-the art colour enhancement network – HDR Net. The loss enforces similarity of the RGB histograms of the predicted and the target images. By providing detailed qualitative and quantitative comparison of different loss functions on varied datasets, we conclude that enforcing similarity in the colour distribution achieves substantial improvement in performance and can play a significant role while choosing loss functions for image enhancement networks.
- Speaker: Aamir Mustafa, University of Cambridge
- Thursday 30 June 2022, 14:00-15:00
- Venue: William Gates Building, Level 2 (Rainbow Corridor), Seminar Room: SS03.
- Series: Rainbow Group Seminars; organiser: am2806.
Thu 30 Jun 12:00: Phenotypic Impact of SARS-CoV-2 Variants
This Talk is now ONLINE ONLY : You may attend with this link: https://zoom.us/j/3099086970?pwd=NDhZc2ZjUkNaOXQ5SlZha1k2QjVZZz09
- Speaker: Dami Aderonke Collier
- Thursday 30 June 2022, 12:00-13:00
- Venue: https://zoom.us/j/3099086970?pwd=NDhZc2ZjUkNaOXQ5SlZha1k2QjVZZz09.
- Series: Cambridge Virology Seminars; organiser: Dr Laura Caller.
Tue 28 Jun 11:00: Noise-Aware Differentially Private Synthetic Data
Synthetic data generated under differential privacy (DP) promises to significantly simplify analysis of sensitive personal data. Existing work has shown that simply analysing DP synthetic data as if it were real does not produce valid inferences of population-level quantities, leading to too narrow confidence intervals and thereby risking false discoveries. We propose using multiple imputation techniques to avoid these problems. This requires simulating multiple synthetic data sets from the Bayesian posterior predictive distribution over data sets. We propose a novel noise-aware Bayesian DP synthetic data generation mechanism for discrete data that enables generating such a distribution of data sets. Our experiments demonstrate that the method is able to produce accurate confidence intervals from DP synthetic data.
- Speaker: Antti Honkela, University of Helsinki
- Tuesday 28 June 2022, 11:00-12:00
- Venue: Hybrid, CBL Seminar room, Department of Engineering, and Zoom https://eng-cam.zoom.us/j/89002493651?pwd=B_2gKl7va_h0CQ9yoMPSbn2ifYLGi4.1.
- Series: Machine Learning @ CUED; organiser: Dr R.E. Turner.
Wed 29 Jun 11:00: The role of meta-learning for few-shot classification
While deep learning has driven impressive progress, one of the toughest remaining challenges is generalization beyond the training distribution. Few-shot learning is an area of research that aims to address this, by striving to build models that can learn new concepts rapidly in a more “human-like” way. While many influential few-shot learning methods were based on meta-learning, recently progress has been made by simpler transfer learning algorithms, and it has been suggested in fact that few-shot learning might be an emergent property of large-scale models. In this talk, I will give an overview of the evolution of few-shot learning methods and benchmarks, with an emphasis on the role of meta-learning on few-shot classification. I will discuss lessons learned from using larger and more diverse benchmarks for evaluation and trade-offs between different approaches, closing with an open discussion about remaining challenges.
- Speaker: Eleni Triantafillou, Google Brain
- Wednesday 29 June 2022, 11:00-12:30
- Venue: Cambridge University Engineering Department, CBL Seminar room BE4-38.
- Series: Machine Learning Reading Group @ CUED; organiser: Elre Oldewage.
Thu 30 Jun 15:00: Trustworthy Digital Identity - Systems Architecture
Governments around the world are committed to supporting the roll out of national digital IDs, but there are privacy and security implications associated with scaling these systems at a national level.
Responsible implementation of ID services is a critical enabler for financial inclusion; it enables access to services and enactment of civil rights. According to the World Bank, more than 1 billion people are currently living without an official digital identity.
Questions of trust are based around the complex interplay of socio-technical considerations, requiring multi-disciplinary expertise. The ‘trustworthiness’ of digital IDs is characterised by multiple inter-related dimensions that include security, privacy, ethics, resilience, robustness and reliability. These dimensions are required to provide the knowledge, tools and guidance needed to implement privacy-preserving, secure identification systems
The project aims to enhance the privacy and security of national digital identity systems, with the ultimate goal to maximise the value to beneficiaries, whilst limiting known and unknown risks to these constituents and maintaining the integrity of the overall system.
- Speaker: Jon Crowcroft, CL and Turing institute
- Thursday 30 June 2022, 15:00-16:00
- Venue: https://cl-cam-ac-uk.zoom.us/j/97216272378?pwd=M2diTFhMTnppckJtNWhFVTBKK0REZz09.
- Series: Computer Laboratory Systems Research Group Seminar; organiser: Srinivasan Keshav.
Wed 29 Jun 16:00: Critical weaknesses in shielding strategies for COVID-19
The COVID -19 pandemic, caused by the coronavirus SARS -CoV-2, has led to a wide range of non-pharmaceutical interventions being implemented around the world to curb transmission. However, the economic and social costs of some of these measures, especially lockdowns, has been high. An alternative and widely discussed public health strategy for the COVID -19 pandemic would have been to `shield’ those most vulnerable to COVID -19 (minimising their contacts with others), while allowing infection to spread among lower risk individuals with the aim of reaching herd immunity. In this talk we will retrospectively explore the effectiveness of such a strategy using a stochastic SEIR framework, showing that even under the unrealistic assumption of perfect shielding, hospitals would have been rapidly overwhelmed with many deaths among lower risk individuals. Crucially, even a small (20%) reduction in the effectiveness of shielding would have likely led to a large increase (>150%) in the number of deaths compared to perfect shielding. Our findings demonstrate that shielding the vulnerable while allowing infections to spread among the wider population would not have been a viable public health strategy for COVID -19 and is unlikely to be effective for future pandemics.
- Speaker: Cameron Smith & Kit Yates, University of Bath
- Wednesday 29 June 2022, 16:00-17:00
- Venue: Zoom.
- Series: Worms and Bugs; organiser: Dr Ciara Dangerfield.