Search Results for author: John Shawe-Taylor

Found 39 papers, 13 papers with code

Progress in Self-Certified Neural Networks

no code implementations15 Nov 2021 Maria Perez-Ortiz, Omar Rivasplata, Emilio Parrado-Hernandez, Benjamin Guedj, John Shawe-Taylor

We then show that in data starvation regimes, holding out data for the test set bounds adversely affects generalisation performance, while self-certified strategies based on PAC-Bayes bounds do not suffer from this drawback, proving that they might be a suitable choice for the small data regime.

Learning PAC-Bayes Priors for Probabilistic Neural Networks

no code implementations21 Sep 2021 Maria Perez-Ortiz, Omar Rivasplata, Benjamin Guedj, Matthew Gleeson, Jingyu Zhang, John Shawe-Taylor, Miroslaw Bober, Josef Kittler

We experiment on 6 datasets with different strategies and amounts of data to learn data-dependent PAC-Bayes priors, and we compare them in terms of their effect on test performance of the learnt predictors and tightness of their risk certificate.

PEEK: A Large Dataset of Learner Engagement with Educational Videos

1 code implementation3 Sep 2021 Sahan Bulathwela, Maria Perez-Ortiz, Erik Novak, Emine Yilmaz, John Shawe-Taylor

One of the main challenges in advancing this research direction is the scarcity of large, publicly available datasets.

Recommendation Systems

A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings

1 code implementation7 Dec 2020 Théophile Cantelobre, Benjamin Guedj, María Pérez-Ortiz, John Shawe-Taylor

Many practical machine learning tasks can be framed as Structured prediction problems, where several output variables are predicted and considered interdependent.

Generalization Bounds Structured Prediction

VLEngagement: A Dataset of Scientific Video Lectures for Evaluating Population-based Engagement

1 code implementation2 Nov 2020 Sahan Bulathwela, Maria Perez-Ortiz, Emine Yilmaz, John Shawe-Taylor

This paper introduces VLEngagement, a novel dataset that consists of content-based and video-specific features extracted from publicly available scientific video lectures and several metrics related to user engagement.

Tighter risk certificates for neural networks

1 code implementation25 Jul 2020 María Pérez-Ortiz, Omar Rivasplata, John Shawe-Taylor, Csaba Szepesvári

In the context of probabilistic neural networks, the output of training is a probability distribution over network weights.

Model Selection

PAC-Bayes Analysis Beyond the Usual Bounds

no code implementations NeurIPS 2020 Omar Rivasplata, Ilja Kuzborskij, Csaba Szepesvari, John Shawe-Taylor

Specifically, we present a basic PAC-Bayes inequality for stochastic kernels, from which one may derive extensions of various known PAC-Bayes bounds as well as novel bounds.

PAC-Bayes unleashed: generalisation bounds with unbounded losses

no code implementations12 Jun 2020 Maxime Haddouche, Benjamin Guedj, Omar Rivasplata, John Shawe-Taylor

We present new PAC-Bayesian generalisation bounds for learning problems with unbounded loss functions.

Predicting Engagement in Video Lectures

1 code implementation31 May 2020 Sahan Bulathwela, María Pérez-Ortiz, Aldo Lipani, Emine Yilmaz, John Shawe-Taylor

The explosion of Open Educational Resources (OERs) in the recent years creates the demand for scalable, automatic approaches to process and evaluate OERs, with the end goal of identifying and recommending the most suitable educational materials for learners.

Recommendation Systems

Correlated Feature Selection with Extended Exclusive Group Lasso

no code implementations27 Feb 2020 Yuxin Sun, Benny Chain, Samuel Kaski, John Shawe-Taylor

In many high dimensional classification or regression problems set in a biological context, the complete identification of the set of informative features is often as important as predictive accuracy, since this can provide mechanistic insight and conceptual understanding.

Feature Selection

Towards an Integrative Educational Recommender for Lifelong Learners

1 code implementation3 Dec 2019 Sahan Bulathwela, Maria Perez-Ortiz, Emine Yilmaz, John Shawe-Taylor

One of the most ambitious use cases of computer-assisted learning is to build a recommendation system for lifelong learning.

TrueLearn: A Family of Bayesian Algorithms to Match Lifelong Learners to Open Educational Resources

1 code implementation21 Nov 2019 Sahan Bulathwela, Maria Perez-Ortiz, Emine Yilmaz, John Shawe-Taylor

The recent advances in computer-assisted learning systems and the availability of open educational resources today promise a pathway to providing cost-efficient, high-quality education to large masses of learners.

Knowledge Tracing

Data-Driven Malaria Prevalence Prediction in Large Densely-Populated Urban Holoendemic sub-Saharan West Africa: Harnessing Machine Learning Approaches and 22-years of Prospectively Collected Data

no code implementations18 Jun 2019 Biobele J. Brown, Alexander A. Przybylski, Petru Manescu, Fabio Caccioli, Gbeminiyi Oyinloye, Muna Elmi, Michael J. Shaw, Vijay Pawar, Remy Claveau, John Shawe-Taylor, Mandayam A. Srinivasan, Nathaniel K. Afolabi, Adebola E. Orimadegun, Wasiu A. Ajetunmobi, Francis Akinkunmi, Olayinka Kowobari, Kikelomo Osinusi, Felix O. Akinbami, Samuel Omokhodion, Wuraola A. Shokunbi, Ikeoluwa Lagunju, Olugbemiro Sodeinde, Delmiro Fernandez-Reyes

Our Locality-specific Elastic-Net based Malaria Prediction System (LEMPS) achieves good generalization performance, both in magnitude and direction of the prediction, when tasked to predict monthly prevalence on previously unseen validation data (MAE<=6x10-2, MSE<=7x10-3) within a range of (+0. 1 to -0. 05) error-tolerance which is relevant and usable for aiding decision-support in a holoendemic setting.

Model Validation Using Mutated Training Labels: An Exploratory Study

no code implementations24 May 2019 Jie M. Zhang, Mark Harman, Benjamin Guedj, Earl T. Barr, John Shawe-Taylor

MV mutates training data labels, retrains the model against the mutated data, then uses the metamorphic relation that captures the consequent training performance changes to assess model fit.

General Classification Model Selection

Structured Multi-Label Biomedical Text Tagging via Attentive Neural Tree Decoding

1 code implementation EMNLP 2018 Gaurav Singh, James Thomas, Iain J. Marshall, John Shawe-Taylor, Byron C. Wallace

We propose a model for tagging unstructured texts with an arbitrary number of terms drawn from a tree-structured vocabulary (i. e., an ontology).

Faster Convergence & Generalization in DNNs

no code implementations30 Jul 2018 Gaurav Singh, John Shawe-Taylor

Deep neural networks have gained tremendous popularity in last few years.

General Classification

Spatiotemporal Prediction of Ambulance Demand using Gaussian Process Regression

no code implementations28 Jun 2018 Seth Nabarro, Tristan Fletcher, John Shawe-Taylor

Accurately predicting when and where ambulance call-outs occur can reduce response times and ensure the patient receives urgent care sooner.

GPR

Adaptive Mechanism Design: Learning to Promote Cooperation

3 code implementations11 Jun 2018 Tobias Baumann, Thore Graepel, John Shawe-Taylor

In the future, artificial learning agents are likely to become increasingly widespread in our society.

Empirical Risk Minimization under Fairness Constraints

2 code implementations NeurIPS 2018 Michele Donini, Luca Oneto, Shai Ben-David, John Shawe-Taylor, Massimiliano Pontil

It encourages the conditional risk of the learned classifier to be approximately constant with respect to the sensitive variable.

Fairness

Improving Active Learning in Systematic Reviews

no code implementations29 Jan 2018 Gaurav Singh, James Thomas, John Shawe-Taylor

The first step in a systematic review task is to identify all the studies relevant to the review.

Active Learning

A Tutorial on Canonical Correlation Methods

1 code implementation7 Nov 2017 Viivi Uurtio, João M. Monteiro, Jaz Kandola, John Shawe-Taylor, Delmiro Fernandez-Reyes, Juho Rousu

Canonical correlation analysis is a family of multivariate statistical methods for the analysis of paired sets of variables.

Probabilistic map-matching using particle filters

no code implementations29 Nov 2016 Kira Kempinska, Toby Davies, John Shawe-Taylor

Increasing availability of vehicle GPS data has created potentially transformative opportunities for traffic management, route planning and other location-based services.

Improved Particle Filters for Vehicle Localisation

no code implementations15 Nov 2016 Kira Kempinska, John Shawe-Taylor

The ability to track a moving vehicle is of crucial importance in numerous applications.

Neighborhood Sensitive Mapping for Zero-Shot Classification using Independently Learned Semantic Embeddings

no code implementations26 May 2016 Gaurav Singh, Fabrizio Silvestri, John Shawe-Taylor

In a traditional setting, classifiers are trained to approximate a target function $f:X \rightarrow Y$ where at least a sample for each $y \in Y$ is presented to the training algorithm.

General Classification Zero-Shot Learning

Localized Lasso for High-Dimensional Regression

no code implementations22 Mar 2016 Makoto Yamada, Koh Takeuchi, Tomoharu Iwata, John Shawe-Taylor, Samuel Kaski

We introduce the localized Lasso, which is suited for learning models that are both interpretable and have a high predictive power in problems with high dimensionality $d$ and small sample size $n$.

Learning Shared Representations in Multi-task Reinforcement Learning

no code implementations7 Mar 2016 Diana Borsa, Thore Graepel, John Shawe-Taylor

We investigate a paradigm in multi-task reinforcement learning (MT-RL) in which an agent is placed in an environment and needs to learn to perform a series of tasks, within this space.

PinView: Implicit Feedback in Content-Based Image Retrieval

no code implementations2 Oct 2014 Zakria Hussain, Arto Klami, Jussi Kujala, Alex P. Leung, Kitsuchart Pasupa, Peter Auer, Samuel Kaski, Jorma Laaksonen, John Shawe-Taylor

It then retrieves images with a specialized online learning algorithm that balances the tradeoff between exploring new images and exploiting the already inferred interests of the user.

Content-Based Image Retrieval

PAC-Bayes Analysis of Multi-view Learning

no code implementations21 Jun 2014 Shiliang Sun, John Shawe-Taylor, Liang Mao

This paper presents eight PAC-Bayes bounds to analyze the generalization performance of multi-view classifiers.

MULTI-VIEW LEARNING

Retrieval of Experiments by Efficient Estimation of Marginal Likelihood

no code implementations19 Feb 2014 Sohan Seth, John Shawe-Taylor, Samuel Kaski

To incorporate this information in the retrieval task, we suggest employing a retrieval metric that utilizes probabilistic models learned from the measurements.

Principled Non-Linear Feature Selection

no code implementations20 Dec 2013 Dimitrios Athanasakis, John Shawe-Taylor, Delmiro Fernandez-Reyes

Recent non-linear feature selection approaches employing greedy optimisation of Centred Kernel Target Alignment(KTA) exhibit strong results in terms of generalisation accuracy and sparsity.

Feature Selection

Learning Non-Linear Feature Maps

no code implementations22 Nov 2013 Dimitrios Athanasakis, John Shawe-Taylor, Delmiro Fernandez-Reyes

Feature selection plays a pivotal role in learning, particularly in areas were parsimonious features can provide insight into the underlying process, such as biology.

Feature Selection

MahNMF: Manhattan Non-negative Matrix Factorization

no code implementations14 Jul 2012 Naiyang Guan, DaCheng Tao, Zhigang Luo, John Shawe-Taylor

This paper presents Manhattan NMF (MahNMF) which minimizes the Manhattan distance between $X$ and $W^T H$ for modeling the heavy tailed Laplacian noise.

A Note on Improved Loss Bounds for Multiple Kernel Learning

no code implementations30 Jun 2011 Zakria Hussain, John Shawe-Taylor, Mario Marchand

In this paper, we correct an upper bound, presented in~\cite{hs-11}, on the generalisation error of classifiers learned through multiple kernel learning.

Cannot find the paper you are looking for? You can Submit a new open access paper.