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.

Paper Reading #5: ChemDataExtractor for Automatic Chemical Database Generation

This Wednesday (4 Dec 2019), Ben Koby presented on his work on the ChemDataExtractor tool which is used to automatically generate databases of chemical information. This is built upon previous work that you can see here.

This was the last paper reading session of the term. We look forward to seeing you again next term!

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.

(Talk) From Pipe Dream to Democratising Cancer Diagnosis with ML | Pandu Raharja-Liu, Co-Founder and CTO of Panakeia

CUMIN had the pleasure to host Pandu Raharja-Liu for a talk on democratising cancer diagnosis with ML this Monday 2 Dec, at the Department of Engineering, Cambridge.

Like our Facebook page or follow our events page to keep up to date with all our future events! Continue reading “(Talk) From Pipe Dream to Democratising Cancer Diagnosis with ML | Pandu Raharja-Liu, Co-Founder and CTO of Panakeia”