Deep non-parametric learning with Gaussian processes Speaker: Andreas Damianou, Sheffield University

This talk will discuss deep Gaussian process models, a recent approach to combining deep probabilistic structures with Bayesian nonparametrics. The obtained deep belief networks are constructed using continuous variables connected with Gaussian process mappings; therefore, the methodology used for training and inference deviates from traditional deep learning paradigms. The first part of the talk will thus outline the associated computational tools, revolving around variational inference. In the second part, we will discuss models obtained as special cases of the deep Gaussian process, namely dynamical / multi-view / dimensionality reduction models and nonparametric autoencoders. The above concepts and algorithms will be demonstrated with examples from computer vision (e.g. high-dimensional video, images) and robotics (motion capture data, humanoid robotics).

Share
Posted in Seminars | Leave a comment

SICSA Computational Interaction Summer School

www.computationalinteraction.org

SICSA Summer School
Computational Interaction
Inference, optimisation and modelling for the engineering of interactive systems
22nd-26th June 2015

School of Computing Science, University of Glasgow

interaction. This will encompass modelling of interaction, deriving and engaging with statistical models of content, automatic learning of preferences and computer-assisted optimisation of interfaces. Applied machine learning and appropriate quantitative analysis, suitable for real-time, closed-loop interactions will be key elements of the summer school school programme.

The course content will include quantitative user modelling, machine learning, intelligent signal processing, crowdsourced and mass-scale interface optimisation techniques and automatic interface optimisation . The school will cover techniques interconnection of large statistical models and low-level interaction primitives, from optimising keyboards from language models, interface layout optimisation from preference learning, synthesising crowdsourced sensor data for ubiquitous computing, to optimising pointing and gesturing.

The distinctive flavour of the school will be in applying these techniques in concrete human-centred applications, with real-world data and real-time, online contexts.

There will be a strong focus on developing applied skills through practical sessions integrated into the school programme, which will give students practical experience in using well-grounded, cutting edge analysis, modelling and inference in engineering interactive systems.

One of the school outcomes will be a self-contained preprepared development and testing environment including development languages and libraries, datasets, links to online resources and the presented course content.

Share
Posted in Seminars, Uncategorized | Comments Off on SICSA Computational Interaction Summer School

Msci Seminars – Dimitar Petrov, Martin Bevc and Demian Till

In the week beginning 20th April, we will have three talks from Msci students, abstracts below:

Tuesday 21st April, 2pm, 423 SAWB: Demian Till (Further Investigating Novelty Search)

Thursday 23rd April, 2pm, 422 SAWB Dimitar Petrov (Improving Touchscreen Typing Using Back-of-Device Grip Interactions) and Martin Bevc (Predicting the Outcome of Tennis Matches From Point-by-Point Data)

Further Investigation Novelty Search – Demian Till

By focussing on objectives, optimisation algorithms tend to waste a lot of time exploring areas of the search space around local optima. In 2008, Lehman and Stanley [1] introduced a new algorithm named ‘novelty search’, which completely ignores the objective and instead directs search based on how much candidates’ behaviours differ from those of previously discovered candidates. In 2011, Lehman and Stanley [2] showed that novelty search significantly outperformed a standard genetic algorithm in the challenging problem of simulated bipedal locomotion. However, the behavioural characterisation used by Lehman and Stanley [2] arguably slipped in a standard fitness function through the back door. This paper demonstrates that novelty search still outperforms ‘objective­based’ search when using a measure of novelty that contains no information about distance travelled. We then introduce a modification of the novelty search algorithm which we show to outperform the original algorithm on the problem of simulated bipedal locomotion. Finally, we investigate the effects of combining novelty search with objective­based search.

[1] Lehman, Joel, and Kenneth O Stanley. “Exploiting Open­Endedness to Solve Problems Through the Search for Novelty.” A​LIFE​5 Aug. 2008: 329­336.

[2] Lehman, Joel, and Kenneth O Stanley. “Abandoning objectives: Evolution through the search for novelty alone.” E​volutionary computation​19.2 (2011): 189­223.

 

Improving Touchscreen Typing Using Back-of-Device Grip Interactions – Dimitar Petrov

Abstract: Typing on touchscreen keyboards is inherently inaccurate as users tend to touch locations offset from their intended target. Offsets are user-specific and can further differ for a given user between postures (left-hand, right-hand, two-hand typing). On the other hand, back-of-device interaction has been used to predict screen touches on randomised abstract targets. We propose a new approach where unique offset models are learned for each posture and back-of-device is used to predict posture. Offset models are learned using linear regression while classification is achieved by SVMs and GPs. The device used is a regular smartphone extended with a capacitive sensor on the back.

 

Predicting the Outcome of Tennis Matches From Point-by-Point Data – Martin Bevc

Tennis is one of the most popular sports in the world and the format of the
game has made it one of the most heavily traded sports in betting markets.
With opportunities for big profits, interest in accurate predictions is high
among professional traders and amateur gamblers.

Traditionally research in predictions of outcomes of tennis matches has focused
on aggregating a lot of historical data and using simple statistical methods to
compute winning probabilities.
The talk will explore modeling tennis matches with Markov chains,
alternative approaches to making outcome predictions
such as simulations, making predictions from in play point by
point data and by sampling points in situations where available data is sparse.
Performance of these methods and techniques used in previous research will
be discussed.

Share
Posted in Seminars | Leave a comment

Seminar: Gait analysis from a single ear-worn sensor

Speaker: Delaram Jarchi
Date: 17 March, 2015
Time: 12:00 – 12:30
Location: Sir Alwyn Williams Building, 303 Meeting Room

Objective assessment of detailed gait patterns is important for clinical applications. One common approach to clinical gait analysis is to use multiple optical or inertial sensors affixed to the patient body for detailed bio-motion and gait analysis. The complexity of sensor placement and issues related to consistent sensor placement have limited these methods only to dedicated laboratory settings, requiring the support of a highly trained technical team. The use of a single sensor for gait assessment has many advantages, particularly in terms of patient compliance, and the possibility of remote monitoring of patients in home environment. In this talk we look into the assessment of a single ear-worn sensor (e-AR sensor) for gait analysis by developing signal processing techniques and using a number of reference platforms inside and outside the gait laboratory. The results are provided considering two clinical applications such as post-surgical follow-up and rehabilitation of orthopaedic patients and investigating the gait changes of the Parkinson’s Disease (PD) patients.

Share
Posted in Seminars | Leave a comment