no code implementations • 16 Oct 2021 • Dino Oglic, Zoran Cvetkovic, Peter Sollich, Steve Renals, Bin Yu
We study the problem of learning robust acoustic models in adverse environments, characterized by a significant mismatch between training and test conditions.
no code implementations • 26 Jan 2021 • Rituparno Mandal, Peter Sollich
Using a Fokker-Planck descriptionwe make testable predictions without any fit parameters for the joint distribution of single particleposition and orientation.
Soft Condensed Matter Disordered Systems and Neural Networks Statistical Mechanics
no code implementations • 7 Dec 2020 • Robin Nicole, Aleksandra Alorić, Peter Sollich
These changes have re-emphasized the importance of understanding the effects of market competition: does proliferation of trading venues and increased competition lead to dominance of a single market or coexistence of multiple markets?
no code implementations • 19 Mar 2020 • Barbara Bravi, Katy J. Rubin, Peter Sollich
We consider the general problem of describing the dynamics of subnetworks of larger biochemical reaction networks, e. g. protein interaction networks involving complex formation and dissociation reactions.
1 code implementation • 23 Jun 2019 • Dino Oglic, Zoran Cvetkovic, Peter Sollich
We investigate the potential of stochastic neural networks for learning effective waveform-based acoustic models.
no code implementations • 29 Jun 2017 • Robin Nicole, Peter Sollich
We therefore compare with the results of Experience-Weighted Attraction (EWA) learning, which at long times leads to Nash equilibria in the appropriate limits of large intensity of choice, low noise (long agent memory) and perfect imputation of missing scores (fictitious play).
no code implementations • 20 Feb 2017 • Adriano Barra, Giuseppe Genovese, Peter Sollich, Daniele Tantari
Restricted Boltzmann Machines are described by the Gibbs measure of a bipartite spin glass, which in turn corresponds to the one of a generalised Hopfield network.
no code implementations • 9 Dec 2016 • Adriano Barra, Giuseppe Genovese, Peter Sollich, Daniele Tantari
We study Generalised Restricted Boltzmann Machines with generic priors for units and weights, interpolating between Boolean and Gaussian variables.
no code implementations • 24 Dec 2013 • Matthew Ager, Zoran Cvetkovic, Peter Sollich
Speech representation and modelling in high-dimensional spaces of acoustic waveforms, or a linear transformation thereof, is investigated with the aim of improving the robustness of automatic speech recognition to additive noise.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 24 Dec 2013 • Jibran Yousafzai, Zoran Cvetkovic, Peter Sollich, Matthew Ager
This work proposes a novel support vector machine (SVM) based robust automatic speech recognition (ASR) front-end that operates on an ensemble of the subband components of high-dimensional acoustic waveforms.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • NeurIPS 2012 • Peter Sollich, Simon Ashton
We study the average case performance of multi-task Gaussian process (GP) regression as captured in the learning curve, i. e.\ the average Bayes error for a chosen task versus the total number of examples $n$ for all tasks.
no code implementations • 6 Nov 2012 • Matthew Urry, Peter Sollich
Our method for predicting the learning curves using belief propagation is significantly more accurate than previous approximations and should become exact in the limit of large random graphs.
no code implementations • NeurIPS 2010 • Matthew Urry, Peter Sollich
We study learning curves for Gaussian process regression which characterise performance in terms of the Bayes error averaged over datasets of a given size.
no code implementations • NeurIPS 2009 • Peter Sollich, Matthew Urry, Camille Coti
The fully correlated limit is reached only once loops become relevant, and we estimate where the crossover to this regime occurs.