Events

Forthcoming events

This page lists C2D3 events, University events, as well as related external conferences and events of interest to our members.

Sarah Sharples Turing Lecture graphic
External event

The Turing Lectures: Where next for self-driving vehicles?

Tuesday, 27 September 2022, 7.00pm to 8.30pm

Organiser: The Alan Turing Institute

In this Turing Lecture, Professor Sarah Sharples will discuss the interface between policy and science for self-driving vehicles, and highlight some of the challenges and opportunities that we face in this area.

Forthcoming talks

A collation of interesting data science talks from across the University.

Theory and Practice of Infinitely Wide Neural Networks - Guest Talk

Wednesday, 28 September 2022, 12.00pm to 1.30pm
Speaker: Roman Novak, Google Brain
Venue: Cambridge University Engineering Department, CBL Seminar room BE4-38

A common observation that wider (in the number of hidden units/channels/attention heads) neural networks perform better motivates studying them in the infinite-width limit.

Remarkably, infinitely wide networks can be easily described in closed form as Gaussian processes (GPs), at initialization, during, and after training—be it gradient-based, or fully Bayesian training. This provides closed-form test set predictions and uncertainties from an infinitely wide network without ever instantiating it (!).

These infinitely wide networks have become powerful models in their own right, establishing several SOTA results, and are used in applications including hyper-parameter selection, neural architecture search, meta learning, active learning, and dataset distillation.

The talk will provide a high-level overview of our work at Google Brain on infinite-width networks. In the first part I will derive core results, providing intuition for why infinite-width networks are GPs. In the second part I will discuss challenges and solutions to implementing and scaling up these GPs. In the third part, I will conclude with example applications made possible with infinite width networks.

The talk does not assume familiarity with the topic beyond general ML background.

Detect – Verify – Communicate: Combating Misinformation with More Realistic NLP

Thursday, 29 September 2022, 12.00pm to 1.00pm
Speaker: Iryna Gurevych
Venue: English Faculty Building, second floor, SR24

Dealing with misinformation is a grand challenge of the information society directed at equipping the computer users with effective tools for identifying and debunking misinformation. Current Natural Language Processing (NLP) including its fact-checking research fails to meet the expectations of real-life scenarios. In this talk, we show why the past work on fact-checking has not yet led to truly useful tools for managing misinformation, and discuss our ongoing work on more realistic solutions. NLP systems are expensive in terms of financial cost, computation, and manpower needed to create data for the learning process. With that in mind, we are pursuing research on detection of emerging misinformation topics to focus human attention on the most harmful, novel examples. Automatic methods for claim verification rely on large, high-quality datasets. To this end, we have constructed two corpora for fact checking, considering larger evidence documents and pushing the state of the art closer to the reality of combating misinformation. We further compare the capabilities of automatic, NLP-based approaches to what human fact checkers actually do, uncovering critical research directions for the future. To edify false beliefs, we are collaborating with cognitive scientists and psychologists to automatically detect and respond to attitudes of vaccine hesitancy, encouraging anti-vaxxers to change their minds with effective communication strategies.

The environmental impact of computational science: how bad is it and what can we do about it?

Monday, 3 October 2022, 1.00pm to 2.00pm
Speaker: Dr Loïc Lannelongue (Department of Public Health and Primary Care)
Venue: Centre for Mathematical Sciences

*Registration is essential.*
The environmental impact of (scientific) computing is a growing concern in light of the urgency of the climate crisis, and there is widespread interest in the research community; so what can we all do about it? Tackling this issue and making it easier for scientists to engage with sustainable computing is what motivated the Green Algorithms project. We will discuss what we learned along the way, how to estimate the impact of our work and what levers scientists and institutions have to make their research more sustainable. We will also debate the ethical implications of these environmental costs and examine what is still needed moving forward.
https://www.c2d3.cam.ac.uk/events/seminar-environmental-impact-computati...

TBA

Tuesday, 4 October 2022, 2.15pm to 3.15pm
Speaker: Danielle Belgrave, DeepMind
Venue: Zoom

"Join us on Zoom":https://zoom.us/j/99166955895?pwd=SzI0M3pMVEkvNmw3Q0dqNDVRalZvdz09

TBA

Efficient priors for self-supervised learning: application and theories

Wednesday, 5 October 2022, 2.00pm to 3.00pm
Speaker: Yu Wang, JD AI Research
Venue: Virtual (see abstract for Zoom link)

Remarkable progress of self-supervised learning has been taking place in the past two years across various domains. The goal of SSL method is to learn useful semantic features without human annotations. In absence of human defined labels, we expect the deep network to learn richer feature structure explained by the data itself instead of being constrained by human knowledge. Nevertheless, self-supervised learning still hinges on strong prior knowledge or human-defined pretext task to effectively pretrain the network. These prior knowledges can impose some certain form of consistency between different views of image, or be based on some pre-defined pretext task such as rotation prediction. This talk will cover our recent progress and new findings in terms of constructing useful priors for self-supervised learning (respectively published in T-PAMI and NeurIPS 2021), both from perspective of theories and practical applications. We will also introduce the SOTA mainstream self-supervised learning frameworks and the useful pretexts widely used in this field.

*Join Zoom Link:*

https://maths-cam-ac-uk.zoom.us/j/93331132587?pwd=MlpReFY3MVpyVThlSi85Tm... Meeting ID: 933 3113 2587 Passcode: 144696

View all talks...