Search Results for author:
Found 43 papers, 8 papers with code
Kernel-Based Anomaly Detection Using Generalized Hyperbolic Processes
We present a novel approach to anomaly detection by integrating Generalized Hyperbolic (GH) processes into kernel-based methods.
Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models
It then refines this approximate concept vector to trigger the concept token with high probability, by perturbing the approximate concept vector with noise and transforming it into token scores with the language model head.
Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models
To this end, we propose a unified taxonomy, which bridges the matrix/tensor compression approaches and model compression concepts in ML and NLP research.
Interpretable Pre-Trained Transformers for Heart Time-Series Data
It is also demonstrated that these pre-trained models are straightforward to fine-tune for tasks such as classification of atrial fibrillation (AF), and beat detection in photoplethysmography.
Demystifying the Hypercomplex: Inductive Biases in Hypercomplex Deep Learning
Hypercomplex algebras have recently been gaining prominence in the field of deep learning owing to the advantages of their division algebras over real vector spaces and their superior results when dealing with multidimensional signals in real-world 3D and 4D paradigms.
Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective
To this end, this work presents the first comprehensive study on improving the adversarial robustness of VLMs against attacks targeting image, text, and multimodal inputs.
Quaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion
We develop a robust quaternion recurrent neural network (QRNN) for real-time processing of 3D and 4D data with outliers.
Widely Linear Matched Filter: A Lynchpin towards the Interpretability of Complex-valued CNNs
However, applying this paradigm to illuminate the interpretability of complex-valued CNNs meets a formidable obstacle: the extension of matched filtering to a general class of noncircular complex-valued data, referred to here as the widely linear matched filter (WLMF), has been only implicit in the literature.
The HR-Calculus: Enabling Information Processing with Quaternion Algebra
From their inception, quaternions and their division algebra have proven to be advantageous in modelling rotation/orientation in three-dimensional spaces and have seen use from the initial formulation of electromagnetic filed theory through to forming the basis of quantum filed theory.
TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition
Taking GPT family models (i. e. GPT-2 and CerebrasGPT) as case studies, our approach theoretically results in $46. 89\%$ fewer parameters of the entire model, with a compression ratio $39. 38\times$ - $65. 64\times$ for the embedding layers.
A Deep Matched Filter For R-Peak Detection in Ear-ECG
Through its operation as a Matched Filter, the encoder searches for matches with an ECG template pattern in the input signal, prior to filtering the matches with the subsequent convolutional layers and selecting peaks corresponding to true ECG matches.
Amplitude-Independent Machine Learning for PPG through Visibility Graphs and Transfer Learning
Photoplethysmography (PPG) refers to the measurement of variations in blood volume using light and is a feature of most wearable devices.
UAdam: Unified Adam-Type Algorithmic Framework for Non-Convex Stochastic Optimization
Adam-type algorithms have become a preferred choice for optimisation in the deep learning setting, however, despite success, their convergence is still not well understood.
Convex Quaternion Optimization for Signal Processing: Theory and Applications
Convex optimization methods have been extensively used in the fields of communications and signal processing.
Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains
Despite the omnipresence of tensors and tensor operations in modern deep learning, the use of tensor mathematics to formally design and describe neural networks is still under-explored within the deep learning community.
Hearables: Ear EEG Based Driver Fatigue Detection
Ear EEG based driver fatigue monitoring systems have the potential to provide a seamless, efficient, and feasibly deployable alternative to existing scalp EEG based systems, which are often cumbersome and impractical.
Rapid Extraction of Respiratory Waveforms from Photoplethysmography: A Deep Encoder Approach
Our model aims to encode all of the relevant respiratory information contained within photoplethysmography waveform, and decode it into a waveform that is similar to a gold standard respiratory reference.
Complexity-based Financial Stress Evaluation
Financial markets typically exhibit dynamically complex properties as they undergo continuous interactions with economic and environmental factors.
Graph-Regularized Tensor Regression: A Domain-Aware Framework for Interpretable Multi-Way Financial Modelling
This represents a challenge for modern machine learning models, as the number of model parameters needed to process such data grows exponentially with the data dimensions; an effect known as the Curse-of-Dimensionality.
Pearl: Parallel Evolutionary and Reinforcement Learning Library
Reinforcement learning is increasingly finding success across domains where the problem can be represented as a Markov decision process.
Variational Embedding Multiscale Sample Entropy:complexity-based analysis for multichannel systems
And this algorithm is tested by both stimulated and real signals.
An Apparatus for the Simulation of Breathing Disorders: Physically Meaningful Generation of Surrogate Data
Overall, the proposed apparatus provides us with a simple, effective and physically meaningful way to generate faithful surrogate breathing disorder waveforms, a prerequisite for the use of artificial intelligence in respiratory health.
Dynamic Portfolio Cuts: A Spectral Approach to Graph-Theoretic Diversification
Stock market returns are typically analyzed using standard regression, yet they reside on irregular domains which is a natural scenario for graph signal processing.
Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecasting
Recurrent Neural Networks (RNNs) represent the de facto standard machine learning tool for sequence modelling, owing to their expressive power and memory.
Graph Theory for Metro Traffic Modelling
Finally, we also explore the application of modern deep learning models, such as graph neural networks and hyper-graph neural networks, as general purpose models for the modelling and forecasting of underground data, especially in the context of the morning and evening rush hours.
Tensor Networks for Multi-Modal Non-Euclidean Data
Modern data sources are typically of large scale and multi-modal natures, and acquired on irregular domains, which poses serious challenges to traditional deep learning models.
Nonstationary Portfolios: Diversification in the Spectral Domain
Classical portfolio optimization methods typically determine an optimal capital allocation through the implicit, yet critical, assumption of statistical time-invariance.
In-Ear SpO2 for Classification of Cognitive Workload
Classification of cognitive workload promises immense benefit in diverse areas ranging from driver safety to augmenting human capability through closed loop brain computer interface.
Multi-Graph Tensor Networks
The irregular and multi-modal nature of numerous modern data sources poses serious challenges for traditional deep learning algorithms.
Recurrent Graph Tensor Networks: A Low-Complexity Framework for Modelling High-Dimensional Multi-Way Sequence
Recurrent Neural Networks (RNNs) are among the most successful machine learning models for sequence modelling, but tend to suffer from an exponential increase in the number of parameters when dealing with large multidimensional data.
A Probabilistic Spectral Analysis of Multivariate Real-Valued Nonstationary Signals
A class of multivariate spectral representations for real-valued nonstationary random variables is introduced, which is characterised by a general complex Gaussian distribution.
In-Ear Measurement of Blood Oxygen Saturation: An Ambulatory Tool Needed To Detect The Delayed Life-Threatening Hypoxaemia in COVID-19
In this study, we set out to establish the feasibility of SpO2 measurement from the ear canal as a convenient site for long term monitoring, and perform a comprehensive comparison with the right index finger - the conventional clinical measurement site.
Tensor Decompositions in Deep Learning
The paper surveys the topic of tensor decompositions in modern machine learning applications.
Supervised Learning for Non-Sequential Data: A Canonical Polyadic Decomposition Approach
However, both TT and other Tensor Networks (TNs), such as Tensor Ring and Hierarchical Tucker, are sensitive to the ordering of their indices (and hence to the features).
Robust Principal Component Analysis Based On Maximum Correntropy Power Iterations
Principal component analysis (PCA) is recognised as a quintessential data analysis technique when it comes to describing linear relationships between the features of a dataset.
Portfolio Cuts: A Graph-Theoretic Framework to Diversification
Investment returns naturally reside on irregular domains, however, standard multivariate portfolio optimization methods are agnostic to data structure.
Compression and Interpretability of Deep Neural Networks via Tucker Tensor Layer: From First Principles to Tensor Valued Back-Propagation
This is achieved through a tensor valued approach, based on the proposed Tucker Tensor Layer (TTL), as an alternative to the dense weight-matrices of DNNs.
Hypergraph $p$-Laplacian: A Differential Geometry View
The proposed $p$-Laplacian is shown to outperform standard hypergraph Laplacians in the experiment on a hypergraph semi-supervised learning and normalized cut setting.
Tensor Valued Common and Individual Feature Extraction: Multi-dimensional Perspective
A novel method for common and individual feature analysis from exceedingly large-scale data is proposed, in order to ensure the tractability of both the computation and storage and thus mitigate the curse of dimensionality, a major bottleneck in modern data science.
Automatic sleep monitoring using ear-EEG
The monitoring of sleep patterns without patient's inconvenience or involvement of a medical specialist is a clinical question of significant importance.
Frequency estimation in three-phase power systems with harmonic contamination: A multistage quaternion Kalman filtering approach
In the first stage a quaternion extended Kalman filter, which provides a unified framework for joint modeling of voltage measurements from all the phases, is used to estimate the instantaneous phase increment of the three-phase voltages.
Quaternion Gradient and Hessian
The optimization of real scalar functions of quaternion variables, such as the mean square error or array output power, underpins many practical applications.
Higher-Order Partial Least Squares (HOPLS): A Generalized Multi-Linear Regression Method
A new generalized multilinear regression model, termed the Higher-Order Partial Least Squares (HOPLS), is introduced with the aim to predict a tensor (multiway array) $\tensor{Y}$ from a tensor $\tensor{X}$ through projecting the data onto the latent space and performing regression on the corresponding latent variables.
