Search Results for author: Christopher K. I. Williams

Found 31 papers, 16 papers with code

Structured Generative Models for Scene Understanding

no code implementations7 Feb 2023 Christopher K. I. Williams

This approach also requires scene models which account for the co-occurrences and inter-relationships of objects in a scene.

Scene Understanding

Multi-Task Dynamical Systems

1 code implementation8 Oct 2022 Alex Bird, Christopher K. I. Williams, Christopher Hawthorne

Time series datasets are often composed of a variety of sequences from the same domain, but from different entities, such as individuals, products, or organizations.

Multi-Task Learning Time Series +1

Inference and Learning for Generative Capsule Models

no code implementations7 Sep 2022 Alfredo Nazabal, Nikolaos Tsagkas, Christopher K. I. Williams

In this paper we specify a generative model for such data, and derive a variational algorithm for inferring the transformation of each model object in a scene, and the assignments of observed parts to the objects.


On Suspicious Coincidences and Pointwise Mutual Information

no code implementations15 Mar 2022 Christopher K. I. Williams

We then discuss the mutual information (MI) and pointwise mutual information (PMI), which depend on the ratio $P(A, B)/P(A)P(B)$, as measures of association.

Align-Deform-Subtract: An Interventional Framework for Explaining Object Differences

no code implementations9 Mar 2022 Cian Eastwood, Li Nanbo, Christopher K. I. Williams

Given two object images, how can we explain their differences in terms of the underlying object properties?

counterfactual Object

Persistent Animal Identification Leveraging Non-Visual Markers

2 code implementations13 Dec 2021 Michael P. J. Camilleri, Li Zhang, Rasneer S. Bains, Andrew Zisserman, Christopher K. I. Williams

Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research.

Visual Tracking

Identifying the Units of Measurement in Tabular Data

1 code implementation23 Nov 2021 Taha Ceritli, Christopher K. I. Williams

We consider the problem of identifying the units of measurement in a data column that contains both numeric values and unit symbols in each row, e. g., "5. 2 l", "7 pints".


ptype-cat: Inferring the Type and Values of Categorical Variables

1 code implementation23 Nov 2021 Taha Ceritli, Christopher K. I. Williams

Type inference is the task of identifying the type of values in a data column and has been studied extensively in the literature.

Vocal Bursts Type Prediction

Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration

1 code implementation ICLR 2022 Cian Eastwood, Ian Mason, Christopher K. I. Williams, Bernhard Schölkopf

Existing methods for SFDA leverage entropy-minimization techniques which: (i) apply only to classification; (ii) destroy model calibration; and (iii) rely on the source model achieving a good level of feature-space class-separation in the target domain.

Source-Free Domain Adaptation

On Memorization in Probabilistic Deep Generative Models

1 code implementation6 Jun 2021 Gerrit J. J. van den Burg, Christopher K. I. Williams

Recent advances in deep generative models have led to impressive results in a variety of application domains.

Density Estimation Memorization

Automating Data Science: Prospects and Challenges

no code implementations12 May 2021 Tijl De Bie, Luc De Raedt, José Hernández-Orallo, Holger H. Hoos, Padhraic Smyth, Christopher K. I. Williams

Given the complexity of typical data science projects and the associated demand for human expertise, automation has the potential to transform the data science process.

AutoML BIG-bench Machine Learning

Inference for Generative Capsule Models

2 code implementations11 Mar 2021 Alfredo Nazabal, Nikolaos Tsagkas, Christopher K. I. Williams

Capsule networks (see e. g. Hinton et al., 2018) aim to encode knowledge and reason about the relationship between an object and its parts.


The Effect of Class Imbalance on Precision-Recall Curves

no code implementations3 Jul 2020 Christopher K. I. Williams

In this note I study how the precision of a classifier depends on the ratio $r$ of positive to negative cases in the test set, as well as the classifier's true and false positive rates.

VAEs in the Presence of Missing Data

1 code implementation9 Jun 2020 Mark Collier, Alfredo Nazabal, Christopher K. I. Williams

Real world datasets often contain entries with missing elements e. g. in a medical dataset, a patient is unlikely to have taken all possible diagnostic tests.

Imputation Missing Elements

An Evaluation of Change Point Detection Algorithms

3 code implementations13 Mar 2020 Gerrit J. J. van den Burg, Christopher K. I. Williams

Next, we present a benchmark study where 14 algorithms are evaluated on each of the time series in the data set.

Change Point Detection Time Series +1

ptype: Probabilistic Type Inference

1 code implementation22 Nov 2019 Taha Ceritli, Christopher K. I. Williams, James Geddes

Type inference refers to the task of inferring the data type of a given column of data.

Vocal Bursts Type Prediction

Customizing Sequence Generation with Multi-Task Dynamical Systems

1 code implementation11 Oct 2019 Alex Bird, Christopher K. I. Williams

Dynamical system models (including RNNs) often lack the ability to adapt the sequence generation or prediction to a given context, limiting their real-world application.

Style Transfer

Robust Variational Autoencoders for Outlier Detection and Repair of Mixed-Type Data

1 code implementation15 Jul 2019 Simão Eduardo, Alfredo Nazábal, Christopher K. I. Williams, Charles Sutton

We show experimentally that not only RVAE performs better than several state-of-the-art methods in cell outlier detection and repair for tabular data, but also that is robust against the initial hyper-parameter selection.

Imputation Outlier Detection

The Extended Dawid-Skene Model: Fusing Information from Multiple Data Schemas

1 code implementation4 Jun 2019 Michael P. J. Camilleri, Christopher K. I. Williams

While label fusion from multiple noisy annotations is a well understood concept in data wrangling (tackled for example by the Dawid-Skene (DS) model), we consider the extended problem of carrying out learning when the labels themselves are not consistently annotated with the same schema.

Multi-Task Time Series Analysis applied to Drug Response Modelling

no code implementations21 Mar 2019 Alex Bird, Christopher K. I. Williams, Christopher Hawthorne

Time series models such as dynamical systems are frequently fitted to a cohort of data, ignoring variation between individual entities such as patients.

Multi-Task Learning Time Series +1

Learning Direct Optimization for Scene Understanding

no code implementations18 Dec 2018 Lukasz Romaszko, Christopher K. I. Williams, John Winn

We develop a Learning Direct Optimization (LiDO) method for the refinement of a latent variable model that describes input image x.

Scene Understanding

Inverting Supervised Representations with Autoregressive Neural Density Models

no code implementations1 Jun 2018 Charlie Nash, Nate Kushman, Christopher K. I. Williams

In addition, we can use these inversion models to estimate the mutual information between a model's inputs and its intermediate representations, thus quantifying the amount of information preserved by the network at different stages.

Density Estimation

Autoencoders and Probabilistic Inference with Missing Data: An Exact Solution for The Factor Analysis Case

1 code implementation11 Jan 2018 Christopher K. I. Williams, Charlie Nash, Alfredo Nazábal

We show how to calculate exactly the latent posterior distribution for the factor analysis (FA) model in the presence of missing data, and note that this solution implies that a different encoder network is required for each pattern of missingness.

A Framework for the Quantitative Evaluation of Disentangled Representations

2 code implementations ICLR 2018 Cian Eastwood, Christopher K. I. Williams

Recent AI research has emphasised the importance of learning disentangled representations of the explanatory factors behind data.

Model Criticism in Latent Space

1 code implementation13 Nov 2017 Sohan Seth, Iain Murray, Christopher K. I. Williams

Model criticism is usually carried out by assessing if replicated data generated under the fitted model looks similar to the observed data, see e. g. Gelman, Carlin, Stern, and Rubin [2004, p. 165].

Gaussian Processes

Predicting Patient State-of-Health using Sliding Window and Recurrent Classifiers

no code implementations2 Dec 2016 Adam McCarthy, Christopher K. I. Williams

Bedside monitors in Intensive Care Units (ICUs) frequently sound incorrectly, slowing response times and desensitising nurses to alarms (Chambrin, 2001), causing true alarms to be missed (Hug et al., 2011).

Time Series Time Series Analysis

Input-Output Non-Linear Dynamical Systems applied to Physiological Condition Monitoring

no code implementations31 Jul 2016 Konstantinos Georgatzis, Christopher K. I. Williams, Christopher Hawthorne

We present a non-linear dynamical system for modelling the effect of drug infusions on the vital signs of patients admitted in Intensive Care Units (ICUs).

Tree-Cut for Probabilistic Image Segmentation

no code implementations11 Jun 2015 Shell X. Hu, Christopher K. I. Williams, Sinisa Todorovic

This paper presents a new probabilistic generative model for image segmentation, i. e. the task of partitioning an image into homogeneous regions.

Image Segmentation Segmentation +2

Discriminative Switching Linear Dynamical Systems applied to Physiological Condition Monitoring

no code implementations24 Apr 2015 Konstantinos Georgatzis, Christopher K. I. Williams

We present a Discriminative Switching Linear Dynamical System (DSLDS) applied to patient monitoring in Intensive Care Units (ICUs).

Renewal Strings for Cleaning Astronomical Databases

no code implementations7 Aug 2014 Amos J. Storkey, Nigel C. Hambly, Christopher K. I. Williams, Robert G. Mann

Large astronomical databases obtained from sky surveys such as the SuperCOSMOS Sky Surveys (SSS) invariably suffer from a small number of spurious records coming from artefactual effects of the telescope, satellites and junk objects in orbit around earth and physical defects on the photographic plate or CCD.

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