arXiv subjects

Danilo P. Mandic

Publications and source records attributed to Danilo P. Mandic.

At least 19 recordsLinked to original sources

arXiv2025

Short Ticketing Detection Framework Analysis Report

This report presents a comprehensive analysis of an unsupervised multi-expert machine learning framework for detecting short ticketing fraud in railway systems. The study introduces an A/B/C/D station classification system that successfully identifies suspicious patterns across 30 high-risk stations. The framework employs four complementary algorithms: Isolation Forest, Local Outlier Factor, One-Class SVM, and Mahalanobis Distance. Key findings include the identification of five distinct short ticketing patterns and potential for short ticketing recovery in transportation systems.

cs.CR↗

arXiv2025

Versatile Cardiovascular Signal Generation with a Unified Diffusion Transformer

Cardiovascular signals such as photoplethysmography (PPG), electrocardiography (ECG), and blood pressure (BP) are inherently correlated and complementary, together reflecting the health of cardiovascular system. However, their joint utilization in real-time monitoring is severely limited by diverse acquisition challenges from noisy wearable recordings to burdened invasive procedures. Here we propose UniCardio, a multi-modal diffusion transformer that reconstructs low-quality signals and synthesizes unrecorded signals in a unified generative framework. Its key innovations include a specialized model architecture to manage the signal modalities involved in generation tasks and a continual learning paradigm to incorporate varying modality combinations. By exploiting the complementary nature of cardiovascular signals, UniCardio clearly outperforms recent task-specific baselines in signal denoising, imputation, and translation. The generated signals match the performance of ground-truth signals in detecting abnormal health conditions and estimating vital signs, even in unseen domains, while ensuring interpretability for human experts. These advantages position UniCardio as a promising avenue for advancing AI-assisted healthcare.

cs.LG↗

arXiv2025

TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices

Small Language Models (SLMs, or on-device LMs) have significantly fewer parameters than Large Language Models (LLMs). They are typically deployed on low-end devices, like mobile phones and single-board computers. Unlike LLMs, which rely on increasing model size for better generalisation, SLMs designed for edge applications are expected to have adaptivity to the deployment environments and energy efficiency given the device battery life constraints, which are not addressed in datacenter-deployed LLMs. This paper addresses these two requirements by proposing a training-free token embedding compression approach using Tensor-Train Decomposition (TTD). Each pre-trained token embedding vector is converted into a lower-dimensional Matrix Product State (MPS). We comprehensively evaluate the extracted low-rank structures across compression ratio, language task performance, latency, and energy consumption on a typical low-end device, i.e. Raspberry Pi. Taking the sub-billion parameter versions of GPT-2/Cerebres-GPT and OPT models as examples, our approach achieves a comparable language task performance to the original model with around $2.0\times$ embedding layer compression, while the energy consumption of a single query drops by half.

cs.CL↗

arXiv2025

A Quantum of Learning: Using Quaternion Algebra to Model Learning on Quantum Devices

This article considers the problem of designing adaption and optimisation techniques for training quantum learning machines. To this end, the division algebra of quaternions is used to derive an effective model for representing computation and measurement operations on qubits. In turn, the derived model, serves as the foundation for formulating an adaptive learning problem on principal quantum learning units, thereby establishing quantum information processing units akin to that of neurons in classical approaches. Then, leveraging the modern HR-calculus, a comprehensive training framework for learning on quantum machines is developed. The quaternion-valued model accommodates mathematical tractability and establishment of performance criteria, such as convergence conditions.

quant-ph↗

arXiv2025

Augmentation of EEG and ECG Time Series for Deep Learning Applications: Integrating Changepoint Detection into the iAAFT Surrogates

The performance of deep learning methods critically depends on the quality and quantity of the available training data. This is especially the case for physiological time series, which are both noisy and scarce, which calls for data augmentation to artificially increase the size of datasets. Another issue is that the time-evolving statistical properties of nonstationary signals prevent the use of standard data augmentation techniques. To this end, we introduce a novel method for augmenting nonstationary time series. This is achieved by combining offline changepoint detection with the iterative amplitude-adjusted Fourier transform (iAAFT), which ensures that the time-frequency properties of the original signal are preserved during augmentation. The proposed method is validated through comparisons of the performance of i) a deep learning seizure detection algorithm on both the original and augmented versions of the CHB-MIT and Siena scalp electroencephalography (EEG) databases, and ii) a deep learning atrial fibrillation (AF) detection algorithm on the original and augmented versions of the Computing in Cardiology Challenge 2017 dataset. By virtue of the proposed method, for the CHB-MIT and Siena datasets respectively, accuracy rose by 4.4% and 1.9%, precision by 10% and 5.5%, recall by 3.6% and 0.9%, and F1 by 4.2% and 1.4%. For the AF classification task, accuracy rose by 0.3%, precision by 2.1%, recall by 0.8%, and F1 by 2.1%.

eess.SP↗

arXiv2025

How can representation dimension dominate structurally pruned LLMs?

Pruning assumes a subnetwork exists in the original deep neural network, which can achieve comparative model performance with less computation than the original. However, it is unclear how the model performance varies with the different subnetwork extractions. In this paper, we choose the representation dimension (or embedding dimension, model dimension, the dimension of the residual stream in the relevant literature) as the entry point to this issue. We investigate the linear transformations in the LLM transformer blocks and consider a specific structured pruning approach, SliceGPT, to extract the subnetworks of different representation dimensions. We mechanistically analyse the activation flow during the model forward passes, and find the representation dimension dominates the linear transformations, model predictions, and, finally, the model performance. Explicit analytical relations are given to calculate the pruned model performance (perplexity and accuracy) without actual evaluation, and are empirically validated with Llama-3-8B-Instruct and Phi-3-mini-4k-Instruct.

cs.LG↗

arXiv2025

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. The GH distribution, known for its flexibility in modeling skewness, heavy tails, and kurtosis, helps to capture complex patterns in data that deviate from Gaussian assumptions. We propose a GH-based kernel function and utilize it within Kernel Density Estimation (KDE) and One-Class Support Vector Machines (OCSVM) to develop anomaly detection frameworks. Theoretical results confirmed the positive semi-definiteness and consistency of the GH-based kernel, ensuring its suitability for machine learning applications. Empirical evaluation on synthetic and real-world datasets showed that our method improves detection performance in scenarios involving heavy-tailed and asymmetric or imbalanced distributions. https://github.com/paulinebourigault/GHKernelAnomalyDetect

cs.LG↗

arXiv2024

Targeted Angular Reversal of Weights (TARS) for Knowledge Removal in Large Language Models

The sheer scale of data required to train modern large language models (LLMs) poses significant risks, as models are likely to gain knowledge of sensitive topics such as bio-security, as well the ability to replicate copyrighted works. Methods designed to remove such knowledge must do so from all prompt directions, in a multi-lingual capacity and without degrading general model performance. To this end, we introduce the targeted angular reversal (TARS) method of knowledge removal from LLMs. The TARS method firstly leverages the LLM in combination with a detailed prompt to aggregate information about a selected concept in the internal representation space of the LLM. 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. The feedforward weight vectors in the LLM which operate directly on the internal representation space, and have the highest cosine similarity with this targeting vector, are then replaced by a reversed targeting vector, thus limiting the ability of the concept to propagate through the model. The modularity of the TARS method allows for a sequential removal of concepts from Llama 3.1 8B, such as the famous literary detective Sherlock Holmes, and the planet Saturn. It is demonstrated that the probability of triggering target concepts can be reduced to 0.00 with as few as 1 TARS edit, whilst simultaneously removing the knowledge bi-directionally. Moreover, knowledge is shown to be removed across all languages despite only being targeted in English. Importantly, TARS has minimal impact on the general model capabilities, as after removing 5 diverse concepts in a modular fashion, there is minimal KL divergence in the next token probabilities of the LLM on large corpora of Wikipedia text (median of 0.0015).

cs.CL↗

arXiv2024

Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective

Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primarily focused on enhancing the robustness of image encoders against image-based attacks, with defenses against text-based and multimodal attacks remaining largely unexplored. 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. This is achieved by proposing multimodal contrastive adversarial training (MMCoA). Such an approach strengthens the robustness of both image and text encoders by aligning the clean text embeddings with adversarial image embeddings, and adversarial text embeddings with clean image embeddings. The robustness of the proposed MMCoA is examined against existing defense methods over image, text, and multimodal attacks on the CLIP model. Extensive experiments on 15 datasets across two tasks reveal the characteristics of different adversarial defense methods under distinct distribution shifts and dataset complexities across the three attack types. This paves the way for a unified framework of adversarial robustness against different modality attacks, opening up new possibilities for securing VLMs against multimodal attacks. The code is available at https://github.com/ElleZWQ/MMCoA.git.

cs.CV↗

arXiv2024

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. Despite their impressive versatility in modelling real-world phenomena, adaptive information processing techniques specifically designed for quaternion-valued signals have only recently come to the attention of the machine learning, signal processing, and control communities. The most important development in this direction is introduction of the HR-calculus, which provides the required mathematical foundation for deriving adaptive information processing techniques directly in the quaternion domain. In this article, the foundations of the HR-calculus are revised and the required tools for deriving adaptive learning techniques suitable for dealing with quaternion-valued signals, such as the gradient operator, chain and product derivative rules, and Taylor series expansion are presented. This serves to establish the most important applications of adaptive information processing in the quaternion domain for both single-node and multi-node formulations. The article is supported by Supplementary Material, which will be referred to as SM.

stat.ML↗

arXiv2024

TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition

High-dimensional token embeddings underpin Large Language Models (LLMs), as they can capture subtle semantic information and significantly enhance the modelling of complex language patterns. However, this high dimensionality also introduces considerable model parameters and prohibitively high model storage and memory requirements, which is particularly unaffordable for low-end devices. Targeting no extra training data and insufficient computation cases, we propose a training-free model compression approach based on the Tensor-Train Decomposition (TTD), whereby each pre-trained token embedding is converted into a lower-dimensional Matrix Product State (MPS). We then comprehensively investigate the low-rank structures extracted by this approach, in terms of the compression ratio, the language task performance, and latency on a typical low-end device (i.e. Raspberry Pi). 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. With different hyperparameter choices, the model compressed with our approach can achieve a comparable language task performance to the original model with around $2.0\times$ embedding layer compression. This empirically proves the existence of low-rank structure in GPT family models, and demonstrates that about half of the parameters in the embedding layers are redundant.

cs.CL↗

arXiv2024

Geometry is All You Need: A Unified Taxonomy of Matrix and Tensor Factorization for Compression of Generative Language Models

Matrix and tensor-guided parametrization for Natural Language Processing (NLP) models is fundamentally useful for the improvement of the model's systematic efficiency. However, the internal links between these two algebra structures and language model parametrization are poorly understood. Also, the existing matrix and tensor research is math-heavy and far away from machine learning (ML) and NLP research concepts. These two issues result in the recent progress on matrices and tensors for model parametrization being more like a loose collection of separate components from matrix/tensor and NLP studies, rather than a well-structured unified approach, further hindering algorithm design. To this end, we propose a unified taxonomy, which bridges the matrix/tensor compression approaches and model compression concepts in ML and NLP research. Namely, we adopt an elementary concept in linear algebra, that of a subspace, which is also the core concept in geometric algebra, to reformulate the matrix/tensor and ML/NLP concepts (e.g. attention mechanism) under one umbrella. In this way, based on our subspace formalization, typical matrix and tensor decomposition algorithms can be interpreted as geometric transformations. Finally, we revisit recent literature on matrix- or tensor-guided language model compression, rephrase and compare their core ideas, and then point out the current research gap and potential solutions.

cs.CL↗

arXiv2024

In-ear ECG Signal Enhancement with Denoising Convolutional Autoencoders

The cardiac dipole has been shown to propagate to the ears, now a common site for consumer wearable electronics, enabling the recording of electrocardiogram (ECG) signals. However, in-ear ECG recordings often suffer from significant noise due to their small amplitude and the presence of other physiological signals, such as electroencephalogram (EEG), which complicates the extraction of cardiovascular features. This study addresses this issue by developing a denoising convolutional autoencoder (DCAE) to enhance ECG information from in-ear recordings, producing cleaner ECG outputs. The model is evaluated using a dataset of in-ear ECGs and corresponding clean Lead I ECGs from 45 healthy participants. The results demonstrate a substantial improvement in signal-to-noise ratio (SNR), with a median increase of 5.9 dB. Additionally, the model significantly improved heart rate estimation accuracy, reducing the mean absolute error by almost 70% and increasing R-peak detection precision to a median value of 90%. We also trained and validated the model using a synthetic dataset, generated from real ECG signals, including abnormal cardiac morphologies, corrupted by pink noise. The results obtained show effective removal of noise sources with clinically plausible waveform reconstruction ability.

eess.SP↗

arXiv2024

Interpretable Pre-Trained Transformers for Heart Time-Series Data

Decoder-only transformers are the backbone of the popular generative pre-trained transformer (GPT) series of large language models. In this work, we employ this framework to the analysis of clinical heart time-series data, to create two pre-trained general purpose cardiac models, termed PPG-PT and ECG-PT. We place a special emphasis on making both such pre-trained models fully interpretable. This is achieved firstly through aggregate attention maps which show that, in order to make predictions, the model focuses on similar points in previous cardiac cycles and gradually broadens its attention in deeper layers. Next, we show that tokens with the same value, which occur at different distinct points in the electrocardiography (ECG) and photoplethysmography (PPG) cycle, form separate clusters in high dimensional space. The clusters form according to phase, as the tokens propagate through the transformer blocks. Finally, we highlight that individual attention heads respond to specific physiologically relevent features, such as the dicrotic notch in PPG and the P-wave in ECG. 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. For the example of AF, the fine-tuning took 11 minutes of computer time, and achieved the respective leave-one-subject-out AUCs of 0.99 and 0.93 for ECG and PPG within the MIMIC Perform AF dataset. In addition, the fine-tuned beat detector achieved a state-of-the-art F1 score of 98%, as well as uniquely providing a beat confidence level which acts as a signal quality estimator. Importantly, the fine-tuned models for AF screening are also fully explainable, with attention shifting to regions in the context that are strongly indicative of atrial fibrillation.

cs.LG↗

arXiv2024

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. This paper provides a foundational framework that serves as a roadmap for understanding why hypercomplex deep learning methods are so successful and how their potential can be exploited. Such a theoretical framework is described in terms of inductive bias, i.e., a collection of assumptions, properties, and constraints that are built into training algorithms to guide their learning process toward more efficient and accurate solutions. We show that it is possible to derive specific inductive biases in the hypercomplex domains, which extend complex numbers to encompass diverse numbers and data structures. These biases prove effective in managing the distinctive properties of these domains, as well as the complex structures of multidimensional and multimodal signals. This novel perspective for hypercomplex deep learning promises to both demystify this class of methods and clarify their potential, under a unifying framework, and in this way promotes hypercomplex models as viable alternatives to traditional real-valued deep learning for multidimensional signal processing.

cs.LG↗

arXiv2024

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. This is achieved by combining the real-time recurrent learning (RTRL) algorithm and the maximum correntropy criterion (MCC) as a loss function. While both the mean square error and maximum correntropy criterion are viable cost functions, it is shown that the non-quadratic maximum correntropy loss function is less sensitive to outliers, making it suitable for applications with multidimensional noisy or uncertain data. Both algorithms are derived based on the novel generalised HR (GHR) calculus, which allows for the differentiation of real functions of quaternion variables and offers the product and chain rules, thus enabling elegant and compact derivations. Simulation results in the context of motion prediction of chest internal markers for lung cancer radiotherapy, which includes regular and irregular breathing sequences, support the analysis.

cs.LG↗

arXiv2024

Widely Linear Matched Filter: A Lynchpin towards the Interpretability of Complex-valued CNNs

A recent study on the interpretability of real-valued convolutional neural networks (CNNs) {Stankovic_Mandic_2023CNN} has revealed a direct and physically meaningful link with the task of finding features in data through matched filters. 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. To this end, to establish the interpretability of the operation of complex-valued CNNs, we introduce a general WLMF paradigm, provide its solution and undertake analysis of its performance. For rigor, our WLMF solution is derived without imposing any assumption on the probability density of noise. The theoretical advantages of the WLMF over its standard strictly linear counterpart (SLMF) are provided in terms of their output signal-to-noise-ratios (SNRs), with WLMF consistently exhibiting enhanced SNR. Moreover, the lower bound on the SNR gain of WLMF is derived, together with condition to attain this bound. This serves to revisit the convolution-activation-pooling chain in complex-valued CNNs through the lens of matched filtering, which reveals the potential of WLMFs to provide physical interpretability and enhance explainability of general complex-valued CNNs. Simulations demonstrate the agreement between the theoretical and numerical results.

cs.LG↗

arXiv2024

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. The PPG signals provide insight into the body's circulatory system and can be employed to extract various bio-features, such as heart rate and vascular ageing. Although several algorithms have been proposed for this purpose, many exhibit limitations, including heavy reliance on human calibration, high signal quality requirements, and a lack of generalisation. In this paper, we introduce a PPG signal processing framework that integrates graph theory and computer vision algorithms, to provide an analysis framework which is amplitude-independent and invariant to affine transformations. It also requires minimal preprocessing, fuses information through RGB channels and exhibits robust generalisation across tasks and datasets. The proposed VGTL-net achieves state-of-the-art performance in the prediction of vascular ageing and demonstrates robust estimation of continuous blood pressure waveforms.

eess.SP↗