University of Cambridge > Talks.cam > AI+Pizza > AI+Pizza April 2018

AI+Pizza April 2018

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

 Please note, this event may be recorded. Microsoft will own the copyright of any recording and reserves the right to distribute it as required.

Title Learning ambient magnetic fields for localisation and mapping Speaker Arno Solin Host Sebastian Nowozin Event Date 20/04/2018 5:30PM – 5:45PM Location Auditorium

Description Small disturbances in the Earth ambient magnetic field can be used as features in indoor positioning. In this talk I present a recent method for online modelling and mapping ambient magnetic fields by Gaussian processes. The mapping approach extends well to simultaneous localisation and mapping (SLAM) by a Rao-Blackwellised particle filter (Sequential Monte Carlo). I present examples of the method running on data collected on a smartphone here in Cambridge. (Joint work with Manon Kok and others)

Title Meta Reinforcement Learning with Latent Variable Gaussian Processes Speaker Steindor Saemundsson Event Date 20/04/2018 5:45PM – 6:00PM Location Auditorium Mode Room Only Description Data efficiency, i.e., learning from small data sets, is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of learning algorithms by generalizing learned concepts from a set of training tasks to unseen, but related, tasks. Often, this relationship between tasks is hard coded or relies in some other way on human expertise. In this paper, we propose to automatically learn the relationship between tasks using a latent variable model. Our approach finds a variational posterior over tasks and averages over all plausible (according to this posterior) tasks when making predictions. We apply this framework within a model-based reinforcement learning setting for learning dynamics models and controllers of many related tasks. We apply our framework in a model-based reinforcement learning setting, and show that our model effectively generalizes to novel tasks.

This talk is part of the AI+Pizza series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2018 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity