Peter Tino

• PhD
• Chair at University of Birmingham

Applications of interpretable machine learning (ML) techniques on medical datasets facilitate early and fast diagnoses, along with getting deeper insight into the data. Furthermore, the transparency of these models increase trust among application domain experts. Medical datasets face common issues such as heterogeneous measurements, imbalanced cla...

Background Theoretical models of conduct disorder (CD) highlight that deficits in emotion recognition, learning, and regulation play a pivotal role in CD etiology. With CD being more prevalent in boys than girls, various theories aim to explain this sex difference. The “differential threshold” hypothesis suggests greater emotion dysfunction in cond...

The successful application of modern machine learning for time series classification is often hampered by limitations in quality and quantity of available training data. To overcome these limitations, available domain expert knowledge in the form of parametrised mechanistic dynamical models can be used whenever it is available and time series obser...

As globular clusters (GCs) orbit the Milky Way, their stars are tidally stripped and form tidal tails that follow the orbit of the cluster around the Galaxy. The morphology of these tails is complex and shows correlations with the phase of orbit and the orbital angular velocity, especially for GCs on eccentric orbits. Here we focus on two GCs, NGC...

This paper explores the representational structure of linear Simple Cycle Reservoirs (SCR) operating at the edge of stability. We view SCR as providing in their state space feature representations of the input-driving time series. By endowing the state space with the canonical dot-product, we ``reverse engineer" the corresponding kernel (inner prod...

As globular clusters (GCs) orbit the Milky Way, their stars are tidally stripped forming tidal tails that follow the orbit of the clusters around the Galaxy. The morphology of these tails is complex and shows correlations with the phase of the orbit and the orbital angular velocity, especially for GCs on eccentric orbits. Here, we focus on two GCs,...

Growing attention has been brought to the fact that many real directed networks exhibit hierarchy and directionality as measured through techniques like trophic analysis and non-normality. We propose a simple growing network model where the probability of connecting to a node is defined by a preferential attachment mechanism based on degree and the...

Reservoir Computing (RC) models, a subclass of recurrent neural networks, are distinguished by their fixed, non-trainable input layer and dynamically coupled reservoir, with only the static readout layer being trained. This design circumvents the issues associated with backpropagating error signals through time, thereby enhancing both stability and...

Aims. Our objectives are to map the filamentary network around the Fornax-Eridanus complex and probe the influence of the local environment on galaxy morphology. Methods. We employed the novel machine-learning tool, named, 1-Dimensional, Recovery, Extraction, and Analysis of Manifolds (1-DREAM) to detect and model filaments around the Fornax cluste...

Our objectives are to map the filamentary network around the Fornax-Eridanus Complex and probe the influence of the local environment on galaxy morphology. We employ the novel machine-learning tool, 1-DREAM (1-Dimensional, Recovery, Extraction, and Analysis of Manifolds) to detect and model filaments around the Fornax cluster. We then use the morph...

Background Predicting dementia early has major implications for clinical management and patient outcomes. Yet, we still lack sensitive tools for stratifying patients early, resulting in patients being undiagnosed or wrongly diagnosed. Despite rapid expansion in machine learning models for dementia prediction, limited model interpretability and gene...

Nowadays, neural network (NN) and deep learning (DL) techniques are widely adopted in many applications, including recommender systems. Given the sparse and stochastic nature of collaborative filtering (CF) data, recent works have critically analyzed the effective improvement of neural-based approaches compared to simpler and often transparent algo...

Reservoir computation models form a subclass of recurrent neural networks with fixed non-trainable input and dynamic coupling weights. Only the static readout from the state space (reservoir) is trainable, thus avoiding the known problems with propagation of gradient information backwards through time. Reservoir models have been successfully applie...

Predicting the course of neurodegenerative disorders early has potential to greatly improve clinical management and patient outcomes. A key challenge for early prediction in real-world clinical settings is the lack of labeled data (i.e., clinical diagnosis). In contrast to supervised classification approaches that require labeled data, we propose a...

Reservoir computing originates in the early 2000s, the core idea being to utilize dynamical systems as reservoirs (nonlinear generalizations of standard bases) to adaptively learn spatiotemporal features and hidden patterns in complex time series. Shown to have the potential of achieving higher-precision prediction in chaotic systems, those pioneer...

The interstellar medium of galaxies is filled with holes, bubbles, and shells, typically interpreted as remnants of stellar evolution. There is growing interest in the study of their properties to investigate stellar and supernova feedback. So far, the detection of cavities in observational and numerical data is mostly done visually and, hence, is...

Background Predicting neurodegenerative disorders early has major implications for timely clinical management and patient outcomes. Despite advances in medical technology, we still lack tools to precisely stratify patients for targeted interventions. Here, we propose an unsupervised modelling approach based on mixtures of state space models that le...

Background Recent advances in machine learning highlight the potential of Ai‐guided tools for early dementia prediction with major implications for timely clinical management. Yet, we still lack robust tools for predicting neurocognitive decline early in clinical practice. We have developed a predictive prognostic model based on Generalised Matrix...

The halo of the Milky Way galaxy hosts multiple dynamically coherent substructures known as stellar streams that are remnants of tidally disrupted orbiting systems such as globular clusters (GCs) and dwarf galaxies (DGs). A particular case is that of the Jhelum stream, which is known for its unusual and complex morphology. Using the available data...

Introduction: The inverse problem of electrocardiography noninvasively localizes the origin of undesired cardiac activity, such as a premature ventricular contraction (PVC), from potential recordings from multiple torso electrodes. However, the optimal number and placement of electrodes for an accurate solution of the inverse problem remain undeter...

Knowing which nodes are influential in a complex network and whether the network can be influenced by a small subset of nodes is a key part of network analysis. However, many traditional measures of importance focus on node level information without considering the global network architecture. We use the method of trophic analysis to study directed...

This paper investigates the problem of dynamic workflow scheduling in cloud computing. In a real-time scenario, the only available information is input data size, and the other task execution requirements, such as execution time, memory consumption, and output data size, must be estimated. In this study, we ask whether a more accurate estimation of...

Reservoir computation models form a subclass of recurrent neural networks with fixed non-trainable input and dynamic coupling weights. Only the static readout from the state space (reservoir) is trainable, thus avoiding the known problems with propagation of gradient information backwards through time. Reservoir models have been successfully applie...

Experience is known to facilitate our ability to interpret sequences of events and make predictions about the future by extracting temporal regularities in our environments. Here, we ask whether uncertainty in dynamic environments affects our ability to learn predictive structures. We exposed participants to sequences of symbols determined by first...

In many real, directed networks, the strongly connected component of nodes which are mutually reachable is very small. This does not fit with current theory, based on random graphs, according to which strong connectivity depends on mean degree and degree–degree correlations. And it has important implications for other properties of real networks an...

Human Immunodeficiency virus (HIV) and its clinical entity, the Acquired Immunodeficiency Syndrome (AIDS) continue to represent an important health burden worldwide. Although great advances have been made towards determining the way viral genetic diversity affects clinical outcome, genetic association studies have been hindered by the complexity of...

The distribution of galaxies and clusters of galaxies on the mega-parsec scale of the Universe follows an intricate pattern now famously known as the Large-Scale Structure or the Cosmic Web. To study the environments of this network, several techniques have been developed that are able to describe its properties and the properties of groups of gala...

The distribution of galaxies and clusters of galaxies on the mega-parsec scale of the Universe follows an intricate pattern now famously known as the Large-Scale Structure or the Cosmic Web. To study the environments of this network, several techniques have been developed that are able to describe its properties and the properties of groups of gala...

Scientific workflows can be represented as directed acyclic graphs (DAGs) with nodes corresponding to individual tasks and directed edges between the nodes signifying the order of task execution. The nodes contain informative attributes related to task-specific data transfer/storage and scheduling length. Given an available amount of (cloud) comput...

Knowing which nodes are influential in a complex network and whether the network can be influenced by a small subset of nodes is a key part of network analysis. However some traditional measures of importance focus on node level information without considering global network architecture. We use the method of Trophic Analysis to study directed netw...

Filamentary structures (one-dimensional manifolds) are ubiquitous in astronomical data sets. Be it in particle simulations or observations, filaments are always tracers of a perturbation in the equilibrium of the studied system and hold essential information on its history and future evolution. However, the recovery of such structures is often comp...

In many real, directed networks, the strongly connected component of nodes which are mutually reachable is very small. This does not fit with current theory, based on random graphs, according to which strong connectivity depends on mean degree and degree-degree correlations. And it has important implications for other properties of real networks an...

Our work presents a geometric approach to pitch estimation (PE)-an important problem in Music Information Retrieval (MIR), and a precursor to a variety of other problems in the field. Though there exist a number of highly-accurate methods , both mono-pitch estimation and multi-pitch estimation (particularly with un-specified polyphonic timbre) prov...

In many classification scenarios, the data to be analyzed can be naturally represented as points living on the curved Riemannian manifold of symmetric positive-definite (SPD) matrices. Due to its non-Euclidean geometry, usual Euclidean learning algorithms may deliver poor performance on such data. We propose a principled reformulation of the succes...

Many real-world networks are directed, sparse, and hierarchical, with a mixture of feedforward and feedback connections with respect to the hierarchy. Moreover, a small number of master nodes are often able to drive the whole system. We study the dynamics of pattern presentation and recovery on sparse, directed, Hopfield-like neural networks using...

Application of interpretable machine learning techniques on medical datasets facilitate early and fast diagnoses, along with getting deeper insight into the data. Furthermore, the transparency of these models increase trust among application domain experts. Medical datasets face common issues such as heterogeneous measurements, imbalanced classes w...

This chapter consisits of several illustrative examples comparing Extended RSDFO with state-of-the-art manifold optimization algorithms such as Riemannian Trust-Region method, Riemannian CMA-ES and Riemannian Particle Swarm Optimization on the n-sphere, Grassmannian manifold, and Jacob’s ladder. Jacob’s ladder, in particular, is a non-compact manif...

The chapter begins by discussing how neither the “geometrical” nor “statistical” approach described in Chap. 4 is suitable for our purpose of establishing a geometrical framework for population-based stochastic optimization on manifolds: the “geometrical” approach is too general whereas the “statistical” approach is too restrictive. We therefore co...

In this chapter, the main algorithm of the book, Extended RSDFO, is described. The chapter begins by formalizing a generalized framework, Riemannian Stochastic Derivative-Free Optimization (RSDFO) algorithms, for adapting Stochastic Derivative-Free Optimization (SDFO) algorithms from Euclidean spaces to Riemannian manifolds. RSDFO encompasses Riema...

Stochastic optimization on Riemannian manifolds is a topic scarcely explored. At the writing of this book, the field is still in its infancy. In this last chapter of the book, the materials discussed throughout the book are wrapped up in a gentle fashion and possible directions for future research are outlined.

This chapter establishes the domain of discourse of the book and formally introduces the essential foundations of Differential Geometry with a flavour towards numerical computation. The chapter is divided into three parts: the first part introduces the notion of topological manifolds. The second part covers necessary objects such as vector bundles,...

Equipped with the product statistical manifold structure of mixture densities, the second part of the book begins by surveying the geometric aspects of two contemporary branches of optimization theories. We first review adaptations of optimization algorithms from Euclidean spaces to Riemannian manifolds, otherwise known as manifold optimization or...

This chapter surveys notions of volume form and intrinsic probability distributions on manifolds in the literature, which can be roughly classified into a “geometrical” approach and a “statistical” approach. The “geometrical” approach focuses on the information geometrical structure of the space of all probability measures on the base manifolds, wh...

In this chapter, the notion of parametrized probability densities over manifolds is extended beyond the confines of a single normal neighbourhood, overcoming the locality of the “statistical” approach described in the previous chapter. In particular, we describe the information geometrical structure of mixture densities over totally bounded subsets...

This chapter describes the geometrical structure of statistical models studied in the emerging field of Information Geometry, formally known as statistical manifolds. Due to the dual nature of statistical manifolds as both a statistical model and a Riemannian manifold, it requires a specialized geometrical structure that is different from the ones...

The kynurenine metabolite is associated with many diseases and disorders, ranging from diabetes and sepsis to more recently COVID-19. Here we report a fluorescence-based assay for the detection of kynurenine in urine using a specific chemosensor, 3-formyl-4-(ethylthio)-7-(diethylamino)-coumarin. The assay produces a linear response at clinically re...

The early stages of Alzheimer’s disease (AD) involve interactions between multiple pathophysiological processes. Although these processes are well studied, we still lack robust tools to predict individualised trajectories of disease progression. Here, we employ a robust and interpretable machine learning approach to combine multimodal biological da...

The presence of manifolds is a common assumption in many applications, including astronomy and computer vision. For instance, in astronomy, low-dimensional stellar structures, such as streams, shells, and globular clusters, can be found in the neighborhood of big galaxies such as the Milky Way. Since these structures are often buried in very large...

Many real-world networks are directed, sparse and hierarchical, with a mixture of feed-forward and feedback connections with respect to the hierarchy. Moreover, a small number of 'master' nodes are often able to drive the whole system. We study the dynamics of pattern presentation and recovery on sparse, directed, Hopfield-like neural networks usin...

Dimensionality reduction and clustering are often used as preliminary steps for many complex machine learning tasks. The presence of noise and outliers can deteriorate the performance of such preprocessing and therefore impair the subsequent analysis tremendously. In manifold learning, several studies indicate solutions for removing background nois...

Learning in the model space (LiMS) represents each observational unit (e.g. sparse and irregular time series) with a suitable model of it (point estimate), or a full posterior distribution over models. LiMS approaches take the mechanistic information of how the data is generated into account, thus enhancing the transparency and interpretability of...

The study of low-dimensional, noisy manifolds embedded in a higher dimensional space has been extremely useful in many applications, from the chemical analysis of multi-phase flows to simulations of galactic mergers. Building a probabilistic model of the manifolds has helped in describing their essential properties and how they vary in space. Howev...

Conduct disorder (CD) with high levels of callous-unemotional traits (CD/HCU) has been theoretically linked to specific difficulties with fear and sadness recognition, in contrast to CD with low levels of callous-unemotional traits (CD/LCU). However, experimental evidence for this distinction is mixed, and it is unclear whether these difficulties a...

This paper presents a geometric approach to pitch estimation (PE) – an important problem in music information retrieval (MIR), and a precursor to a variety of other problems in the field. Though there exist a number of highly accurate methods, both mono-pitch estimation and multi-pitch estimation (particularly with unspecified polyphonic timbre) pr...

In a streaming environment, the characteristics of the data themselves and their relationship with the labels are likely to experience changes as time goes on. Most drift detection methods for supervised data streams are performance-based, that is, they detect changes only after the classication accuracy deteriorates. This may not be sufcient in ma...

Out-of-Distribution (OoD) detectors based on AutoEncoder (AE) rely on an underlying assumption that an AE network cannot reconstruct OoD data as good as in-distribution (ID) data when it is constructed based on ID data only. However, this assumption may be violated in practice, resulting in a degradation in detection performance. Therefore, allevia...

Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people’s trust on deep learning systems. It is also related to many ethical problems, e.g., algorithmic discrimination. Moreover, interpretability is a desired property for deep networks to become powe...

The intrinsic nature of noisy and complex data sets is often concealed in low-dimensional structures embedded in a higher dimensional space. Number of methodologies have been developed to extract and represent such structures in the form of manifolds (i.e. geometric structures that locally resemble continuously deformable intervals of Rj¹). Usually...

Topological data analysis tools enjoy increasing popularity in a wide range of applications, such as Computer graphics, Image analysis, Machine learning, and Astronomy for extracting information. However, due to computational complexity, processing large numbers of samples of higher dimensionality quickly becomes infeasible. This contribution is tw...

Understanding in which circumstances office workers take rest breaks is important for delivering effective mobile notifications and make inferences about their daily lifestyle, e.g., whether they are active and/or have a sedentary life. Previous studies designed for office workers show the effectiveness of rest breaks for preventing work-related co...

In this paper, we develop a new classification method for manifold-valued data in the framework of probabilistic learning vector quantization. In many classification scenarios, the data can be naturally represented by symmetric positive definite matrices, which are inherently points that live on a curved Riemannian manifold. Due to the non-Euclidea...

Reservoir computing is a popular approach to design recurrent neural networks, due to its training simplicity and approximation performance. The recurrent part of these networks is not trained (e.g., via gradient descent), making them appealing for analytical studies by a large community of researchers with backgrounds spanning from dynamical syste...

The use of primary care electronic health records for research is abundant. The benefits gained from utilising such records lies in their size, longitudinal data collection and data quality. However, the use of such data to undertake high quality epidemiological studies, can lead to significant challenges particularly in dealing with misclassificat...

In this paper, we develop a new classification method for manifold-valued data in the framework of probabilistic learning vector quantization. In many classification scenarios, the data can be naturally represented by symmetric positive definite matrices, which are inherently points that live on a curved Riemannian manifold. Due to the non-Euclidea...

This book constitutes the refereed proceedings of the 22nd International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2021, which took place during November 25-27, 2021. The conference was originally planned to take place in Manchester, UK, but was held virtually due to the COVID-19 pandemic. The 61 full papers included...

Along with the great success of deep neural networks, there is also growing concern about their black-box nature. The interpretability issue affects people's trust on deep learning systems. It is also related to many ethical problems, e.g., algorithmic discrimination. Moreover, interpretability is a desired property for deep networks to become powe...

Background Current models of AD pathogenesis hypothesise that b‐amyloid induces downstream tau deposition leading to cognitive decline. Here, we use machine learning with baseline data to predict dynamic changes in cortical tau in preclinical AD populations. Methods Using individuals from the ADNI (n=307) we train a machine learning algorithm that...

This paper presents a geometric approach to pitch estimation (PE)-an important problem in Music Information Retrieval (MIR), and a precursor to a variety of other problems in the field. Though there exist a number of highly-accurate methods, both mono-pitch estimation and multi-pitch estimation (particularly with unspecified polyphonic timbre) prov...

DNA replication initiates from multiple genomic locations called replication origins. In metazoa, DNA sequence elements involved in origin specification remain elusive. Here, we examine pluripotent, primary, differentiating, and immortalized human cells, and demonstrate that a class of origins, termed core origins, is shared by different cell types...

Dimensionality reduction and clustering are often used as preliminary steps for many complex machine learning tasks. The presence of noise and outliers can deteriorate the performance of such preprocessing and therefore impair the subsequent analysis tremendously. In manifold learning, several studies indicate solutions for removing background nois...

The earliest stages of Alzheimer’s disease (AD) involve interactions between multiple pathophysiological processes. Although these processes are well studied, we still lack robust tools to predict individualised trajectories of disease progression. Here, we employ a robust and interpretable machine learning approach to combine multimodal biological...

The earliest stages of Alzheimer’s disease (AD) involve interactions between multiple pathophysiological processes. Although these processes are well studied, we still lack robust tools to predict individualised trajectories of disease progression. Here, we employ a robust and interpretable machine learning approach to combine multimodal biological...

The notion of learning from different problem instances, although an old and known one, has in recent years regained popularity within the optimization community. Notable endeavors have been drawing inspiration from machine learning methods as a means for algorithm selection and solution transfer. However, surprisingly approaches which are centered...

Less is known about the relationship between conduct disorder (CD), callous–unemotional (CU) traits, and positive and negative parenting in youth compared to early childhood. We combined traditional univariate analyses with a novel machine learning classifier (Angle-based Generalized Matrix Learning Vector Quantization) to classify youth ( N = 756;...