Google Talk | Better, faster, stronger: 10 years of computer vision and deep learning

It was a great pleasure to welcome Andreas Steiner from Google to deliver his talk: “Better, faster, stronger: 10 years of computer vision and deep learning” on the 2nd of February. Andreas discussed the history of computer vision, and provided some insight into Google’s latest advances in the field using transformers.

TALK ABSTRACT

The field of computer vision was revolutionized in 2012 with the advent of deep learning. We’re in the year 2021 and the latest results look poised to shake up the field again : Non-convolutional architectures produce state of the art results, and they leverage of large amounts of weakly labelled data leads to impressive results on data never seen during training. This talk will start from the very basics using ML for image classification, dive into transfer learning, and finally focus on recent research results, such as vision transformers and contrastive learning from text and images.

 

SPEAKER BIO

Andreas is a software engineer at Google Zurich. He holds a medical degree from Université de Lausanne and a masters in bioelectronics from ETH Zurich. He’s worked as a civil servant in Tanzania and as a Doctoral Student in the Swiss Tropical and Public Health Institute. He’s been in his current position at Google for 6 years.

Microsoft Research Talk | Bringing Intelligence to the End User

We were delighted to welcome Dr Carina Negreanu and Professor Andy Gordon from Microsoft Research to deliver their talk: “Bringing Intelligence to the End User” on 23rd November. Our speakers discussed how AI could revolutionise the way Excel users interact with spreadsheets, the goals of Microsoft’s Calc Intelligence project, and their experiences working for one of the world’s leading industrial research labs.
Abstract
Calc Intelligence aims to bring intelligence to end-user programming, and in particular to spreadsheets. The spreadsheet has continually evolved to remain at the forefront of productivity tools and work practices for over forty years. For example, today’s spreadsheets embrace collaboration, serve as databases, are mobile, and encompass AI-powered interaction via natural language. However, the soul of the spreadsheet remains the grid, and its formulas. Indeed, spreadsheets are the world’s most widely-used programming technology – but they also embody apparently-fundamental limitations. We are working on foundational ideas that will take a qualitative step forward, to extend dramatically the reach of what end users can do with spreadsheets. In this talk we will give an overview of Calc Intelligence (focusing on our recent ML publications) and share career experiences from two researchers at different career stages (principal researcher and post-doc researcher).
Speaker Bios
Dr Carina Negreanu completed a PhD in modified gravity at the Cavendish, University of Cambridge in 2018, before embarking on a 1 year AI Residency with Microsoft Research. She now works full-time as a ML postdoc researcher in the Calc Intelligence group at Microsoft.
Professor Andy Gordon is a Senior Principal Research Manager at Microsoft Research, Cambridge. His main project is Calc Intelligence, bringing intelligence to end-user programming, especially spreadsheets. As a part-time position, he also holds the Chair in Computer Security in the School of Informatics in the University of Edinburgh. He convenes the University of Edinburgh’s Microsoft Research Joint Initiative in Informatics and participates in the Data Science PhD programme and the Cyber Security & Privacy Research Network.

Samsung AI Talk | Generating Realistic Speech-Driven Facial Animation

Our talk by Dr Stavros Petridis of Samsung AI on Generating Realistic Speech-Driven Facial Animation took place 4pm on Wednesday, 26 Feb, at the Department of Engineering, LT6.

Our next talk is on Thursday, 5 March, by FiveAI, titled Machines that see: what AI can and can’t do. Hope to see you there!

Continue reading “Samsung AI Talk | Generating Realistic Speech-Driven Facial Animation”

Paper Reading #10: Mutual Information Representation Learning

This week’s paper reading was presented by Arun and went over a different approach to representation learning that does not require generative modelling but instead tries to maximise the mutual information between the data and its representation. The link to the paper is below.

Learning deep representations by mutual information estimation and maximization:
https://arxiv.org/abs/1808.06670

Our paper readings take place weekly at the Department of Engineering on Tuesdays 2pm. Hope to see you next week!

Like our Facebook page to keep informed of the other events that we’ll be doing. Check out our paper reading page for information on other regular paper reading groups that are going on around Cambridge.

Paper Reading #9: Normalising flows for discrete data

This week’s paper reading was presented by Arun and introduced normalising flows as a method of performing variational inference and its extension to work on discrete data

Papers:
Variational Inference with Normalizing Flows
https://arxiv.org/abs/1505.05770

and

Discrete Flows: Invertible Generative Models of Discrete Data
https://arxiv.org/abs/1905.10347

Our paper readings take place weekly at the Department of Engineering on Tuesdays 2pm. Hope to see you next week!

Like our Facebook page to keep informed of the other events that we’ll be doing. Check out our paper reading page for information on other regular paper reading groups that are going on around Cambridge.

Paper Reading #8: Causal Methods in RL

This week’s session by Bruno covered the relationship between two interesting areas, RL and causal inference. We went over the two following papers:

Counterfactual Multi-Agent Policy Gradients
https://arxiv.org/abs/1705.08926

and

Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models
https://arxiv.org/abs/1905.05824

Our paper readings take place weekly at the Department of Engineering on Tuesdays 2pm. Hope to see you next week!

Like our Facebook page to keep informed of the other events that we’ll be doing. Check out our paper reading page for information on other regular paper reading groups that are going on around Cambridge.

Paper Reading #7: Discrete Representation Learning

For the second paper reading of Lent 2020, Arun Kumar presented on two papers, “The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables” and “Neural Discrete Representation Learning”.

Our paper readings are now back to running weekly at the Department of Engineering on Tuesdays 2pm. Hope to see you next week!

Like our Facebook page to keep informed of the other events that we’ll be doing. Check out our paper reading page for information on other regular paper reading groups that are going on around Cambridge.

Paper Reading #6: Homomorphically-Encrypted Neural Networks

Our weekly paper reading group is back for Lent term. The first paper, “HEAX: High-Performance Architecture for Computation on Homomorphically Encrypted Data in the Cloud” (Riazi et al. 2019) was presented by Jon Chuang. You can check out the paper here, and if you’re interested in joining Jon’s team for the Xilinx Open Hardware 2020 Competition, you can find out more by emailing him at jcyc3@cam.ac.uk or check out this document.

Like our Facebook page to keep informed of the other events that we’ll be doing. Check out our paper reading page for information on other regular paper reading groups that are going on around Cambridge.