
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...
read it

Probabilistic solution of chaotic dynamical system inverse problems using Bayesian Artificial Neural Networks
This paper demonstrates the application of Bayesian Artificial Neural Ne...
read it

Model inference for Ordinary Differential Equations by parametric polynomial kernel regression
Model inference for dynamical systems aims to estimate the future behavi...
read it

Adequate and fair explanations
Explaining sophisticated machinelearning based systems is an important ...
read it

Regularising Deep Networks with DGMs
Here we develop a new method for regularising neural networks where we l...
read it

A Model to Search for Synthesizable Molecules
Deep generative models are able to suggest new organic molecules by gene...
read it

Scalable Partial Explainability in Neural Networks via Flexible Activation Functions
Achieving transparency in blackbox deep learning algorithms is still an...
read it

Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders
In clustering we normally output one cluster variable for each datapoint...
read it

An Introduction to Probabilistic Programming
This document is designed to be a firstyear graduatelevel introduction...
read it

Robust Variational Autoencoders for Outlier Detection in MixedType Data
We focus on the problem of unsupervised cell outlier detection in mixed ...
read it

On the Constrained Leastcost Tour Problem
We introduce the Constrained Leastcost Tour (CLT) problem: given an und...
read it

Learning a Generative Model for Validity in Complex Discrete Structures
Deep generative models have been successfully used to learn representati...
read it

On denoising modulo 1 samples of a function
Consider an unknown smooth function f: [0,1] →R, and say we are given n ...
read it

Learning Disentangled Representations with SemiSupervised Deep Generative Models
Variational autoencoders (VAEs) learn representations of data by jointly...
read it

ARIGAN: Synthetic Arabidopsis Plants using Generative Adversarial Network
In recent years, there has been an increasing interest in imagebased pl...
read it

VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
Deep generative models provide powerful tools for distributions over com...
read it

Counterfactual Fairness
Machine learning can impact people with legal or ethical consequences wh...
read it

Grammar Variational Autoencoder
Deep generative models have been wildly successful at learning coherent ...
read it

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...
read it

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 ...
read it

Kernel Sequential Monte Carlo
We propose kernel sequential Monte Carlo (KSMC), a framework for samplin...
read it

Emo, Love, and God: Making Sense of Urban Dictionary, a CrowdSourced Online Dictionary
The Internet facilitates largescale collaborative projects. The emergen...
read it

Worstcase Optimal Submodular Extensions for Marginal Estimation
Submodular extensions of an energy function can be used to efficiently c...
read it

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 ...
read it

Hierarchical Disentangled Representations
Deep latentvariable models learn representations of highdimensional da...
read it

Exploring HyperParameter Optimization for Neural Machine Translation on GPU Architectures
Neural machine translation (NMT) has been accelerated by deep learning n...
read it

Predicting Electron Paths
Chemical reactions can be described as the stepwise redistribution of el...
read it

TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
Machine learning methods are widely used for a variety of prediction pro...
read it

Towards an understanding of CNNs: analysing the recovery of activation pathways via Deep Convolutional Sparse Coding
Deep Convolutional Sparse Coding (DCSC) is a framework reminiscent of d...
read it

A diachronic study of historiography
The humanities are often characterized by sociologists as having a low m...
read it

Multikernel unmixing and superresolution using the Modified Matrix Pencil method
Consider L groups of point sources or spike trains, with the l^th group ...
read it

Handling Incomplete Heterogeneous Data using VAEs
Variational autoencoders (VAEs), as well as other generative models, hav...
read it

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...
read it

A Modern Retrospective on Probabilistic Numerics
This article attempts to cast the emergence of probabilistic numerics as...
read it

Efficient Search for Diverse Coherent Explanations
This paper proposes new search algorithms for counterfactual explanation...
read it

The Privacy Blanket of the Shuffle Model
This work studies differential privacy in the context of the recently pr...
read it

GASC: GenreAware Semantic Change for Ancient Greek
Word meaning changes over time, depending on linguistic and extralingui...
read it

Augmenting correlation structures in spatial data using deep generative models
Stateoftheart deep learning methods have shown a remarkable capacity ...
read it

A Bayesian Hierarchical Model for Criminal Investigations
Potential violent criminals will often need to go through a sequence of ...
read it

QUOTIENT: TwoParty Secure Neural Network Training and Prediction
Recently, there has been a wealth of effort devoted to the design of sec...
read it

Conditional Independence Testing using Generative Adversarial Networks
We consider the hypothesis testing problem of detecting conditional depe...
read it

A Robust TwoSample Test for Time Series data
We develop a general framework for hypothesis testing with time series d...
read it

Design choices for productive, secure, dataintensive research at scale in the cloud
We present a policy and process framework for secure environments for pr...
read it

sktime: A Unified Interface for Machine Learning with Time Series
We present sktime  a new scikitlearn compatible Python library with a...
read it

Private Protocols for UStatistics in the Local Model and Beyond
In this paper, we study the problem of computing Ustatistics of degree ...
read it

Green Deep Reinforcement Learning for Radio Resource Management: Architecture, Algorithm Compression and Challenge
AI heralds a stepchange in the performance and capability of wireless n...
read it

Explainable Artificial Intelligence (XAI) for 6G: Improving Trust between Human and Machine
As the 5th Generation (5G) mobile networks are bringing about global soc...
read it

Data Generation for Neural Programming by Example
Programming by example is the problem of synthesizing a program from a s...
read it

Graph Input Representations for Machine Learning Applications in Urban Network Analysis
Understanding and learning the characteristics of network paths has been...
read it

Soft Random Graphs in Probabilistic Metric Spaces Intergraph Distance
We present a new method for learning Soft Random Geometric Graphs (SRGGs...
read it
The Alan Turing Institute
The Alan Turing Institute is the United Kingdom's national institute for data science and artificial intelligence, founded in 2015.