Deep Learning

The BICV group does extensive work with deep learning in our research. For more details, see the Techniques we use.

Deep Learning Network

The purpose of the Deep Learning Network is to unite researchers across Imperial College London working on deep learning by facilitating the sharing of knowledge and experience, and expanding this to the wider deep learning community. There is no formal membership and all are welcome to attend meetings. You may subscribe to the mailing list (for events and general-interest postings) or Slack (for reading groups and general chat).

The group was founded by Kai in 2014 and is run with the help of volunteers both inside and outside of the university; it is not officially endorsed by Imperial College London. For more information about current events or to be added to Slack please contact Pierre.

Reading Group

The reading group happens regularly on Tuesdays at 18:00 in the Electrical and Electronic Engineering building, South Kensington campus; we utilise room 1004 or 1009f depending on availability. All reading groups are listed in the calendar below (which can also indicate when the reading group is not running).

Events

Talks

2017-09-15
Andrew Brock
(Heriot-Watt University/University of Edinburgh)
SMASH: One-Shot Model Architecture Search through Hypernetworks

2017-09-08
Andrew Trask
(University of Oxford/DeepMind)
Proposing Encryption and Federation for Safe AI

2017-09-01
Katja Hofmann
(Microsoft Research)
Minecraft as Playground and Laboratory for Artificial Intelligence

2017-08-18
Yang You
(UC Berkeley)
Large-Batch DNN Training

2017-08-08
Wenzhe Shi
(Magic Pony Twitter)
Neural Networks for Image and Video Super-Resolution

2017-07-03
Alex Kendall
(University of Cambridge)
Geometry in Deep Learning for Computer Vision

2017-05-26
Martín Arjovsky
(New York University)
On Different Distances Between Distributions and Generative Adversarial Networks
 
(organised with the Creative AI Meetup)

2017-01-06
Jane Wang
(Google DeepMind)
Learning to Reinforcement Learn
Slides

2016-11-29
Bob L. Sturm
(Queen Mary University of London)
Some (Mis)Applications of Deep Learning to Music

2016-11-16
Tim Rocktäschel
(University College London)
What Can Deep Learning Learn from Symbolic Inference?

2016-10-09
Miles Brundage
(University of Oxford)
AI Policy: Short and Long Term Considerations

2016-09-29
Doug Orr & Marco Fiscato
(Microsoft SwiftKey)
Neural Language Modelling

2015-12-02
Kai Arulkumaran
(Imperial College London)
Nature vs. Nurture: Biological Parallels to Deep Learning

2015-12-01
Roelof Pieters
(KTH/Graph Technologies)
Creative AI & Multimodality: Looking Ahead

2015-02-11
Dimitrios Korkinof
(Cortexica)
Deep Learning Tutorial Part Two: Generative Models

2015-02-11
Muhammad Awais
(Cortexica)
Deep Learning Tutorial Part One

Presentations

2016-05-06
Continuous Deep Q-Learning with Model-based Acceleration

2016-04-22
Generative Adversarial Networks

2016-01-26
Human-Level Control Through Deep Reinforcement Learning

2015-08-07
Modeling Human Motion Using Binary Latent Variables

2015-06-24
Real-Time Classification and Sensor Fusion with a Spiking Deep Belief Network

2015-06-12
Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition

2015-04-24
End-to-End Training of Deep Visuomotor Policies

Links