Search Results for author: Terry Lyons

Found 42 papers, 19 papers with code

FaceTouch: Detecting hand-to-face touch with supervised contrastive learning to assist in tracing infectious disease

no code implementations24 Aug 2023 Mohamed R. Ibrahim, Terry Lyons

Despite partial occlusion of faces, the introduced system learns to detect face touches from the RGB representation of a given scene by utilising the representation of the body gestures such as arm movement.

Contrastive Learning

Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detection

1 code implementation Computing in Cardiology 2022 Benjamin Walker, Felix Krones, Ivan Kiskin, Guy Parsons, Terry Lyons, Adam Mahdi

The second model is the output of DBRes integrated with demographic data and signal features using XGBoost. DBRes achieved our best weighted accuracy of $0. 771$ on the hidden test set for murmur classification, which placed us fourth for the murmur task.


Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations

no code implementations22 Feb 2023 Tiexin Qin, Benjamin Walker, Terry Lyons, Hong Yan, Haoliang Li

Empirical evaluation on a range of dynamic graph representation learning tasks demonstrates the superiority of our proposed approach compared to the baselines.

Graph Representation Learning

New directions in the applications of rough path theory

no code implementations9 Feb 2023 Adeline Fermanian, Terry Lyons, James Morrill, Cristopher Salvi

This article provides a concise overview of some of the recent advances in the application of rough path theory to machine learning.

Sampling-based Nyström Approximation and Kernel Quadrature

1 code implementation23 Jan 2023 Satoshi Hayakawa, Harald Oberhauser, Terry Lyons

We analyze the Nystr\"om approximation of a positive definite kernel associated with a probability measure.

Learning Theory

Signature Methods in Machine Learning

no code implementations29 Jun 2022 Terry Lyons, Andrew D. McLeod

These insights can be quite naturally translated into numerical approaches to understanding streamed data, and perhaps because of their mathematical precision, have proved useful in analysing streamed data in situations where the data is irregular, and not stationary, and the dimension of the data and the sample sizes are both moderate.

BIG-bench Machine Learning

ImageSig: A signature transform for ultra-lightweight image recognition

no code implementations13 May 2022 Mohamed R. Ibrahim, Terry Lyons

With very few parameters and small size models, the key advantage is that one could have many of these "detectors" assembled on the same chip; moreover, the feature acquisition can be performed once and shared between different models of different tasks - further accelerating the process.

Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition

1 code implementation25 Oct 2021 Shujian Liao, Terry Lyons, Weixin Yang, Kevin Schlegel, Hao Ni

In this paper, we propose a novel module, namely Logsig-RNN, which is the combination of the log-signature layer and recurrent type neural networks (RNNs).

Action Recognition In Videos Skeleton Based Action Recognition +3

Neural Controlled Differential Equations for Online Prediction Tasks

2 code implementations21 Jun 2021 James Morrill, Patrick Kidger, Lingyi Yang, Terry Lyons

This is fine when the whole time series is observed in advance, but means that Neural CDEs are not suitable for use in \textit{online prediction tasks}, where predictions need to be made in real-time: a major use case for recurrent networks.

Irregular Time Series Time Series +1

Efficient and Accurate Gradients for Neural SDEs

2 code implementations NeurIPS 2021 Patrick Kidger, James Foster, Xuechen Li, Terry Lyons

This reduces computational cost (giving up to a $1. 87\times$ speedup) and removes the numerical truncation errors associated with gradient penalty.

SigGPDE: Scaling Sparse Gaussian Processes on Sequential Data

no code implementations10 May 2021 Maud Lemercier, Cristopher Salvi, Thomas Cass, Edwin V. Bonilla, Theodoros Damoulas, Terry Lyons

Making predictions and quantifying their uncertainty when the input data is sequential is a fundamental learning challenge, recently attracting increasing attention.

Gaussian Processes Time Series +2

Modelling Paralinguistic Properties in Conversational Speech to Detect Bipolar Disorder and Borderline Personality Disorder

no code implementations18 Feb 2021 Bo wang, Yue Wu, Nemanja Vaci, Maria Liakata, Terry Lyons, Kate E A Saunders

Bipolar disorder (BD) and borderline personality disorder (BPD) are two chronic mental health conditions that clinicians find challenging to distinguish based on clinical interviews, due to their overlapping symptoms.

Neural SDEs as Infinite-Dimensional GANs

1 code implementation6 Feb 2021 Patrick Kidger, James Foster, Xuechen Li, Harald Oberhauser, Terry Lyons

Stochastic differential equations (SDEs) are a staple of mathematical modelling of temporal dynamics.

Time Series Time Series Analysis

"Hey, that's not an ODE'": Faster ODE Adjoints with 12 Lines of Code

no code implementations1 Jan 2021 Patrick Kidger, Ricky T. Q. Chen, Terry Lyons

Neural differential equations may be trained by backpropagating gradients via the adjoint method, which is another differential equation typically solved using an adaptive-step-size numerical differential equation solver.

Time Series Time Series Analysis

Neural SDEs Made Easy: SDEs are Infinite-Dimensional GANs

no code implementations1 Jan 2021 Patrick Kidger, James Foster, Xuechen Li, Harald Oberhauser, Terry Lyons

Several authors have introduced \emph{Neural Stochastic Differential Equations} (Neural SDEs), often involving complex theory with various limitations.

Information Extraction from Swedish Medical Prescriptions with Sig-Transformer Encoder

no code implementations EMNLP (ClinicalNLP) 2020 John Pougue Biyong, Bo wang, Terry Lyons, Alejo J Nevado-Holgado

Relying on large pretrained language models such as Bidirectional Encoder Representations from Transformers (BERT) for encoding and adding a simple prediction layer has led to impressive performance in many clinical natural language processing (NLP) tasks.

Neural CDEs for Long Time Series via the Log-ODE Method

no code implementations28 Sep 2020 James Morrill, Patrick Kidger, Cristopher Salvi, James Foster, Terry Lyons

Neural Controlled Differential Equations (Neural CDEs) are the continuous-time analogue of an RNN, just as Neural ODEs are analogous to ResNets.

Time Series Time Series Analysis

"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms

2 code implementations20 Sep 2020 Patrick Kidger, Ricky T. Q. Chen, Terry Lyons

Neural differential equations may be trained by backpropagating gradients via the adjoint method, which is another differential equation typically solved using an adaptive-step-size numerical differential equation solver.

Time Series Time Series Analysis

Neural Rough Differential Equations for Long Time Series

3 code implementations17 Sep 2020 James Morrill, Cristopher Salvi, Patrick Kidger, James Foster, Terry Lyons

Neural controlled differential equations (CDEs) are the continuous-time analogue of recurrent neural networks, as Neural ODEs are to residual networks, and offer a memory-efficient continuous-time way to model functions of potentially irregular time series.

Irregular Time Series Time Series +2

The Signature Kernel is the solution of a Goursat PDE

3 code implementations26 Jun 2020 Cristopher Salvi, Thomas Cass, James Foster, Terry Lyons, Weixin Yang

Recently, there has been an increased interest in the development of kernel methods for learning with sequential data.

Dimensionality Reduction Time Series Analysis +1

A Data-driven Market Simulator for Small Data Environments

no code implementations21 Jun 2020 Hans Bühler, Blanka Horvath, Terry Lyons, Imanol Perez Arribas, Ben Wood

Neural network based data-driven market simulation unveils a new and flexible way of modelling financial time series without imposing assumptions on the underlying stochastic dynamics.

Time Series Time Series Analysis

Distribution Regression for Sequential Data

no code implementations10 Jun 2020 Maud Lemercier, Cristopher Salvi, Theodoros Damoulas, Edwin V. Bonilla, Terry Lyons

In this paper, we develop a rigorous mathematical framework for distribution regression where inputs are complex data streams.

regression Time Series +1

Anomaly detection on streamed data

no code implementations5 Jun 2020 Thomas Cochrane, Peter Foster, Terry Lyons, Imanol Perez Arribas

Applying this method to (signatures) of time series and other types of streamed data we provide an effective methodology of broad applicability for identifying anomalous complex multimodal sequential data.

Anomaly Detection Time Series +1

Generalised Interpretable Shapelets for Irregular Time Series

2 code implementations28 May 2020 Patrick Kidger, James Morrill, Terry Lyons

The shapelet transform is a form of feature extraction for time series, in which a time series is described by its similarity to each of a collection of `shapelets'.

Audio Classification Irregular Time Series +2

Neural Controlled Differential Equations for Irregular Time Series

5 code implementations NeurIPS 2020 Patrick Kidger, James Morrill, James Foster, Terry Lyons

The resulting \emph{neural controlled differential equation} model is directly applicable to the general setting of partially-observed irregularly-sampled multivariate time series, and (unlike previous work on this problem) it may utilise memory-efficient adjoint-based backpropagation even across observations.

Irregular Time Series Time Series +1

Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU

1 code implementation ICLR 2021 Patrick Kidger, Terry Lyons

Signatory is a library for calculating and performing functionality related to the signature and logsignature transforms.

Universal Approximation with Deep Narrow Networks

no code implementations21 May 2019 Patrick Kidger, Terry Lyons

The classical Universal Approximation Theorem holds for neural networks of arbitrary width and bounded depth.

Deep Signature Transforms

2 code implementations NeurIPS 2019 Patric Bonnier, Patrick Kidger, Imanol Perez Arribas, Cristopher Salvi, Terry Lyons

The signature is an infinite graded sequence of statistics known to characterise a stream of data up to a negligible equivalence class.

Labelling as an unsupervised learning problem

no code implementations10 May 2018 Terry Lyons, Imanol Perez Arribas

In this paper, we present a challenge whose objective is to discover nonlinear relationships in noisy cloud of points.

Sketching the order of events

no code implementations31 Aug 2017 Terry Lyons, Harald Oberhauser

We introduce features for massive data streams.

A signature-based machine learning model for bipolar disorder and borderline personality disorder

1 code implementation22 Jul 2017 Imanol Perez Arribas, Kate Saunders, Guy Goodwin, Terry Lyons

Participants with bipolar disorder or borderline personality disorder and healthy volunteers completed daily mood ratings using a bespoke smartphone app for up to a year.

BIG-bench Machine Learning Time Series +1

Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition

no code implementations13 Jul 2017 Weixin Yang, Terry Lyons, Hao Ni, Cordelia Schmid, Lianwen Jin

To this end, we regard the evolving landmark data as a high-dimensional path and apply non-linear path signature techniques to provide an expressive, robust, non-linear, and interpretable representation for the sequential events.

Action Classification Action Recognition In Videos +1

Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition

no code implementations9 Oct 2016 Zecheng Xie, Zenghui Sun, Lianwen Jin, Hao Ni, Terry Lyons

Online handwritten Chinese text recognition (OHCTR) is a challenging problem as it involves a large-scale character set, ambiguous segmentation, and variable-length input sequences.

Handwritten Chinese Text Recognition Language Modelling

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