The Alan Turing Institute

research

∙ 07/30/2020

A Recommendation and Risk Classification System for Connecting Rough Sleepers to Essential Outreach Services

Rough sleeping is a chronic problem faced by some of the most disadvanta...

Harrison Wilde, et al. ∙

research

∙ 05/26/2020

Probabilistic solution of chaotic dynamical system inverse problems using Bayesian Artificial Neural Networks

This paper demonstrates the application of Bayesian Artificial Neural Ne...

David K. E. Green, et al. ∙

research

∙ 08/06/2019

Model inference for Ordinary Differential Equations by parametric polynomial kernel regression

Model inference for dynamical systems aims to estimate the future behavi...

David K. E. Green, et al. ∙

research

∙ 01/21/2020

Adequate and fair explanations

Explaining sophisticated machine-learning based systems is an important ...

Nicholas Asher, et al. ∙

research

∙ 09/08/2021

Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values

In high-stakes applications of data-driven decision making like healthca...

Mahed Abroshan, et al. ∙

research

∙ 09/25/2019

Regularising Deep Networks with DGMs

Here we develop a new method for regularising neural networks where we l...

Matthew Willetts, et al. ∙

research

∙ 01/13/2022

Density Estimation from Schlieren Images through Machine Learning

This study proposes a radically alternate approach for extracting quanti...

Bryn Noel Ubald, et al. ∙

research

∙ 06/12/2019

A Model to Search for Synthesizable Molecules

Deep generative models are able to suggest new organic molecules by gene...

John Bradshaw, et al. ∙

research

∙ 06/10/2020

Scalable Partial Explainability in Neural Networks via Flexible Activation Functions

Achieving transparency in black-box deep learning algorithms is still an...

Schyler C. Sun, et al. ∙

research

∙ 09/25/2019

Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders

In clustering we normally output one cluster variable for each datapoint...

Matthew Willetts, et al. ∙

research

∙ 09/27/2018

An Introduction to Probabilistic Programming

This document is designed to be a first-year graduate-level introduction...

Jan-Willem van de Meent, et al. ∙

research

∙ 07/15/2019

Robust Variational Autoencoders for Outlier Detection in Mixed-Type Data

We focus on the problem of unsupervised cell outlier detection in mixed ...

Simão Eduardo, et al. ∙

research

∙ 06/18/2019

On the Constrained Least-cost Tour Problem

We introduce the Constrained Least-cost Tour (CLT) problem: given an und...

Patrick O'Hara, et al. ∙

research

∙ 11/02/2021

AI Ethics Statements – Analysis and lessons learnt from NeurIPS Broader Impact Statements

Ethics statements have been proposed as a mechanism to increase transpar...

Carolyn Ashurst, et al. ∙

research

∙ 12/05/2017

Learning a Generative Model for Validity in Complex Discrete Structures

Deep generative models have been successfully used to learn representati...

David Janz, et al. ∙

research

∙ 10/27/2017

On denoising modulo 1 samples of a function

Consider an unknown smooth function f: [0,1] →R, and say we are given n ...

Mihai Cucuringu, et al. ∙

research

∙ 06/01/2017

Learning Disentangled Representations with Semi-Supervised Deep Generative Models

Variational autoencoders (VAEs) learn representations of data by jointly...

N. Siddharth, et al. ∙

research

∙ 09/04/2017

ARIGAN: Synthetic Arabidopsis Plants using Generative Adversarial Network

In recent years, there has been an increasing interest in image-based pl...

Mario Valerio Giuffrida, et al. ∙

research

∙ 05/22/2017

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning

Deep generative models provide powerful tools for distributions over com...

Akash Srivastava, et al. ∙

research

∙ 03/20/2017

Counterfactual Fairness

Machine learning can impact people with legal or ethical consequences wh...

Matt J. Kusner, et al. ∙

research

∙ 03/06/2017

Grammar Variational Autoencoder

Deep generative models have been wildly successful at learning coherent ...

Matt J. Kusner, et al. ∙

research

∙ 01/01/2017

Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image

We propose a unified formulation for the problem of 3D human pose estima...

Denis Tome, et al. ∙

research

∙ 05/02/2016

Algorithms for Learning Sparse Additive Models with Interactions in High Dimensions

A function f: R^d →R is a Sparse Additive Model (SPAM), if it is of the ...

Hemant Tyagi, et al. ∙

research

∙ 10/11/2015

Kernel Sequential Monte Carlo

We propose kernel sequential Monte Carlo (KSMC), a framework for samplin...

Ingmar Schuster, et al. ∙

research

∙ 12/22/2017

Emo, Love, and God: Making Sense of Urban Dictionary, a Crowd-Sourced Online Dictionary

The Internet facilitates large-scale collaborative projects. The emergen...

Dong Nguyen, et al. ∙

research

∙ 01/10/2018

Worst-case Optimal Submodular Extensions for Marginal Estimation

Submodular extensions of an energy function can be used to efficiently c...

Pankaj Pansari, et al. ∙

research

∙ 03/09/2018

Provably robust estimation of modulo 1 samples of a smooth function with applications to phase unwrapping

Consider an unknown smooth function f: [0,1]^d →R, and say we are given ...

Mihai Cucuringu, et al. ∙

research

∙ 04/06/2018

Hierarchical Disentangled Representations

Deep latent-variable models learn representations of high-dimensional da...

Babak Esmaeili, et al. ∙

research

∙ 05/05/2018

Exploring Hyper-Parameter Optimization for Neural Machine Translation on GPU Architectures

Neural machine translation (NMT) has been accelerated by deep learning n...

Robert Lim, et al. ∙

research

∙ 05/23/2018

Predicting Electron Paths

Chemical reactions can be described as the stepwise redistribution of el...

John Bradshaw, et al. ∙

research

∙ 06/09/2018

TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service

Machine learning methods are widely used for a variety of prediction pro...

Amartya Sanyal, et al. ∙

research

∙ 06/26/2018

Towards an understanding of CNNs: analysing the recovery of activation pathways via Deep Convolutional Sparse Coding

Deep Convolutional Sparse Coding (D-CSC) is a framework reminiscent of d...

Michael Murray, et al. ∙

research

∙ 07/04/2018

A diachronic study of historiography

The humanities are often characterized by sociologists as having a low m...

Giovanni Colavizza, et al. ∙

research

∙ 07/08/2018

Multi-kernel unmixing and super-resolution using the Modified Matrix Pencil method

Consider L groups of point sources or spike trains, with the l^th group ...

Stéphane Chrétien, et al. ∙

research

∙ 07/10/2018

Handling Incomplete Heterogeneous Data using VAEs

Variational autoencoders (VAEs), as well as other generative models, hav...

Alfredo Nazabal, et al. ∙

research

∙ 08/26/2018

Nowcasting the Stance of Social Media Users in a Sudden Vote: The Case of the Greek Referendum

Modelling user voting intention in social media is an important research...

Adam Tsakalidis, et al. ∙

research

∙ 01/14/2019

A Modern Retrospective on Probabilistic Numerics

This article attempts to cast the emergence of probabilistic numerics as...

C. J. Oates, et al. ∙

research

∙ 01/02/2019

Efficient Search for Diverse Coherent Explanations

This paper proposes new search algorithms for counterfactual explanation...

Chris Russell, et al. ∙

research

∙ 03/07/2019

The Privacy Blanket of the Shuffle Model

This work studies differential privacy in the context of the recently pr...

Borja Balle, et al. ∙

research

∙ 03/13/2019

GASC: Genre-Aware Semantic Change for Ancient Greek

Word meaning changes over time, depending on linguistic and extra-lingui...

Valerio Perrone, et al. ∙

research

∙ 05/23/2019

Augmenting correlation structures in spatial data using deep generative models

State-of-the-art deep learning methods have shown a remarkable capacity ...

Konstantin Klemmer, et al. ∙

research

∙ 07/03/2019

A Bayesian Hierarchical Model for Criminal Investigations

Potential violent criminals will often need to go through a sequence of ...

F. O. Bunnin, et al. ∙

research

∙ 07/08/2019

QUOTIENT: Two-Party Secure Neural Network Training and Prediction

Recently, there has been a wealth of effort devoted to the design of sec...

Nitin Agrawal, et al. ∙

research

∙ 07/09/2019

Conditional Independence Testing using Generative Adversarial Networks

We consider the hypothesis testing problem of detecting conditional depe...

Alexis Bellot, et al. ∙

research

∙ 07/09/2019

A Robust Two-Sample Test for Time Series data

We develop a general framework for hypothesis testing with time series d...

Alexis Bellot, et al. ∙

research

∙ 08/23/2019

Design choices for productive, secure, data-intensive research at scale in the cloud

We present a policy and process framework for secure environments for pr...

Diego Arenas, et al. ∙

research

∙ 09/17/2019

sktime: A Unified Interface for Machine Learning with Time Series

We present sktime -- a new scikit-learn compatible Python library with a...

Markus Löning, et al. ∙

research

∙ 10/09/2019

Private Protocols for U-Statistics in the Local Model and Beyond

In this paper, we study the problem of computing U-statistics of degree ...

James Bell, et al. ∙

research

∙ 10/11/2019

Green Deep Reinforcement Learning for Radio Resource Management: Architecture, Algorithm Compression and Challenge

AI heralds a step-change in the performance and capability of wireless n...

Zhiyong Du, et al. ∙

research

∙ 11/11/2019

Explainable Artificial Intelligence (XAI) for 6G: Improving Trust between Human and Machine

As the 5th Generation (5G) mobile networks are bringing about global soc...

Weisi Guo, et al. ∙

The Alan Turing Institute

Featured Researchers