Search Results for author:
Found 42 papers, 19 papers with code
FaceTouch: Detecting hand-to-face touch with supervised contrastive learning to assist in tracing infectious disease
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.
Unbiased Decisions Reduce Regret: Adversarial Domain Adaptation for the Bank Loan Problem
We introduce adversarial optimism (AdOpt) to directly address bias in the training set using adversarial domain adaptation.
Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detection
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.
Ranked #1 on
Classify murmurs
on CirCor DigiScope
Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations
Empirical evaluation on a range of dynamic graph representation learning tasks demonstrates the superiority of our proposed approach compared to the baselines.
New directions in the applications of rough path theory
This article provides a concise overview of some of the recent advances in the application of rough path theory to machine learning.
Benchmarking optimality of time series classification methods in distinguishing diffusions
Statistical optimality benchmarking is crucial for analyzing and designing time series classification (TSC) algorithms.
Sampling-based Nyström Approximation and Kernel Quadrature
We analyze the Nystr\"om approximation of a positive definite kernel associated with a probability measure.
Signature Methods in Machine Learning
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.
ImageSig: A signature transform for ultra-lightweight image recognition
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
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
Higher Order Kernel Mean Embeddings to Capture Filtrations of Stochastic Processes
Stochastic processes are random variables with values in some space of paths.
Positively Weighted Kernel Quadrature via Subsampling
We study kernel quadrature rules with convex weights.
Neural Controlled Differential Equations for Online Prediction Tasks
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.
Efficient and Accurate Gradients for Neural SDEs
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
Making predictions and quantifying their uncertainty when the input data is sequential is a fundamental learning challenge, recently attracting increasing attention.
Modelling Paralinguistic Properties in Conversational Speech to Detect Bipolar Disorder and Borderline Personality Disorder
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
Stochastic differential equations (SDEs) are a staple of mathematical modelling of temporal dynamics.
"Hey, that's not an ODE'": Faster ODE Adjoints with 12 Lines of Code
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.
Neural SDEs Made Easy: SDEs are Infinite-Dimensional GANs
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
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
Neural Controlled Differential Equations (Neural CDEs) are the continuous-time analogue of an RNN, just as Neural ODEs are analogous to ResNets.
"Hey, that's not an ODE": Faster ODE Adjoints via Seminorms
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.
Neural Rough Differential Equations for Long Time Series
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.
Ranked #4 on
Time Series Classification
on EigenWorms
Learning to Detect Bipolar Disorder and Borderline Personality Disorder with Language and Speech in Non-Clinical Interviews
Bipolar disorder (BD) and borderline personality disorder (BPD) are both chronic psychiatric disorders.
The Signature Kernel is the solution of a Goursat PDE
Recently, there has been an increased interest in the development of kernel methods for learning with sequential data.
A Data-driven Market Simulator for Small Data Environments
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.
Distribution Regression for Sequential Data
In this paper, we develop a rigorous mathematical framework for distribution regression where inputs are complex data streams.
Anomaly detection on streamed data
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.
A Generalised Signature Method for Multivariate Time Series Feature Extraction
There is a great deal of flexibility as to how this method can be applied.
Generalised Interpretable Shapelets for Irregular Time Series
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'.
Neural Controlled Differential Equations for Irregular Time Series
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.
Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU
Signatory is a library for calculating and performing functionality related to the signature and logsignature transforms.
Learning stochastic differential equations using RNN with log signature features
We illustrate the approach by approximating the unknown functional as a controlled differential equation.
Ranked #51 on
Skeleton Based Action Recognition
on NTU RGB+D 120
Universal Approximation with Deep Narrow Networks
The classical Universal Approximation Theorem holds for neural networks of arbitrary width and bounded depth.
Deep Signature Transforms
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
In this paper, we present a challenge whose objective is to discover nonlinear relationships in noisy cloud of points.
Detecting early signs of depressive and manic episodes in patients with bipolar disorder using the signature-based model
Recurrent major mood episodes and subsyndromal mood instability cause substantial disability in patients with bipolar disorder.
A signature-based machine learning model for bipolar disorder and borderline personality disorder
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.
Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition
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.
Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
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.
Learning from the past, predicting the statistics for the future, learning an evolving system
We bring the theory of rough paths to the study of non-parametric statistics on streamed data.
