Andrea Soltoggio

Andrea Soltoggio
Loughborough University | Lough · Department of Computer Science

PhD

About

68
Publications
21,100
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
689
Citations
Additional affiliations
May 2014 - present
Loughborough University
Position
  • Lecturer
January 2010 - April 2014
Bielefeld University
Position
  • EU Integration Project Technical Coordinator
January 2010 - April 2014
Bielefeld University
Position
  • EU Integration Project Technical Coordinator

Publications

Publications (68)
Conference Paper
Full-text available
Through their breath, humans exhale hundreds of volatile organic compounds (VOCs) that can reveal pathologies, including many types of cancer at early stages. Gas chromatography-mass spectrometry (GC-MS) is an analytical method used to separate and detect compounds in the mixture contained in breath samples. The identification of VOCs is based on t...
Article
Full-text available
Asynchrony in sensory-motor signals and variable delays between causes and effects introduce ambiguity as to which stimuli, actions, and rewards are causally related. Only the repetition of reward episodes help distinguish true cause-effect relationships from coincidental occurrences. In the model proposed here, a form of short-term plasticity gene...
Article
Full-text available
In the course of trial-and-error learning, the results of actions, manifested as rewards or punishments, occur often seconds after the actions that caused them. How can a reward be associated with an earlier action when the neural activity that caused that action is no longer present in the network? This problem is referred to as the distal reward...
Article
Synaptic plasticity is a major mechanism for adaptation, learning, and memory. Yet current models struggle to link local synaptic changes to the acquisition of behaviors. The aim of this paper is to demonstrate a computational relationship between local Hebbian plasticity and behavior learning by exploiting two traditionally unwanted features: neur...
Article
Full-text available
memory in biological neural networks. Similarly, artificial neural networks could benefit from modulatory dynamics when facing certain types of learning problem. Here we test this hypothesis by introducing modulatory neurons to enhance or dampen neural plasticity at target neural nodes. Simulated evolution is employed to design neural control netwo...
Article
Full-text available
Volatile organic compounds (VOCs) in human breath can reveal a large spectrum of health conditions and can be used for fast, accurate and non-invasive diagnostics. Gas chromatography-mass spectrometry (GC-MS) is used to measure VOCs, but its application is limited by expert-driven data analysis that is time-consuming, subjective and may introduce e...
Article
Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments. Such a feat is achieved through dynamic representations in an agent’s policy network (obtained via reasoning about task context, model parameter updates, or both). However, obtaining rich dynamic representations for fas...
Article
Biological organisms learn from interactions with their environment throughout their lifetime. For artificial systems to successfully act and adapt in the real world, it is desirable to similarly be able to learn on a continual basis. This challenge is known as lifelong learning, and remains to a large extent unsolved. In this Perspective article,...
Preprint
Full-text available
Learning from set-structured data is an essential problem with many applications in machine learning and computer vision. This paper focuses on non-parametric and data-independent learning from set-structured data using approximate nearest neighbor (ANN) solutions, particularly locality-sensitive hashing. We consider the problem of set retrieval fr...
Preprint
Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments. Such a feat is achieved through dynamic representations in an agent's policy network (obtained via reasoning about task context, model parameter updates, or both). However, obtaining rich dynamic representations for fas...
Article
In this article, we consider a subclass of partially observable Markov decision process (POMDP) problems which we termed confounding POMDPs. In these types of POMDPs, temporal difference (TD)-based reinforcement learning (RL) algorithms struggle, as TD error cannot be easily derived from observations. We solve these types of problems using a new bi...
Preprint
Full-text available
A bstract Flexible planning is necessary for reaching goals and adapting when conditions change. We introduce a biologically plausible path planning model that learns its environment, rapidly adapts to change, and plans efficient routes to goals. Unlike prior models of hippocamapl replay, our model addresses the decision-making process when faced w...
Article
Due to safety requirements for Human-Robot Interaction (HRI), industrial robots have to meet high standards of safety requirements (ISO 10218). However, even if robots are incapable of causing serious physical harm, they still may influence people's mental and emotional wellbeing, as well as their trust, behaviour and performance in close collabora...
Article
Full-text available
The ability of an agent to detect changes in an environment is key to successful adaptation. This ability involves at least two phases: learning a model of an environment, and detecting that a change is likely to have occurred when this model is no longer accurate. This task is particularly challenging in partially observable environments, such as...
Preprint
Full-text available
A wide range of techniques can be considered for segmentation of images of nanostructured surfaces. Manually segmenting these images is time-consuming and results in a user-dependent segmentation bias, while there is currently no consensus on the best automated segmentation methods for particular techniques, image classes, and samples. Any image se...
Article
Full-text available
Volatile organic compounds (VOCs) in human breath can reveal a large spectrum of health conditions and can be used for fast, accurate and non-invasive diagnostics. Gas chromatography-mass spectrometry (GC-MS) is used to measure VOCs, but its application is limited by expert-driven data analysis that is time-consuming, subjective and may introduce e...
Preprint
Volatile organic compounds (VOCs) in human breath can reveal a large spectrum of health conditions and can be used for fast, accurate and non-invasive diagnostics. Gas chromatography-mass spectrometry (GC-MS) is used to measure VOCs, but its application is limited by expert-driven data analysis that is time-consuming, subjective and may introduce e...
Article
Full-text available
The scarcity of high-resolution urban digital elevation model (DEM) datasets, particularly in certain developing countries, has posed a challenge for many water-related applications such as flood risk management. A solution to address this is to develop effective approaches to reconstruct high-resolution DEMs from their low-resolution equivalents t...
Preprint
Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning. However, reinforcement learning (RL) algorithms struggle in POMDP environments because the state of the system, essential in a RL framework, is not always visible. Additionally, hand-designed meta-RL architect...
Article
Metabolic profiling of breath analysis involves processing, alignment, scaling and clustering of thousands of features ex-tracted from Gas Chromatography Mass spectrometry (GC-MS) data from hundreds of participants. The multi-step data processing is complicated, operator error-prone and time-consuming. Automated algorithmic clustering methods that...
Conference Paper
As industry automation is evolving, the barriers between humans and machines are slowly disappearing. With humans and intelligent robots working closer together it is imperative to ensure not only physical safety but also the mental and emotional well-being of the workers. This paper uses the HTC Vive Virtual Reality headset to simulate different H...
Preprint
Full-text available
This paper introduces the modulated Hebbian plus Q network architecture (MOHQA) for solving challenging partially observable Markov decision processes (POMDPs) deep reinforcement learning problems with sparse rewards and confounding observations. The proposed architecture combines a deep Q-network (DQN), and a modulated Hebbian network with neural...
Preprint
Full-text available
The shortage of high-resolution urban digital elevation model (DEM) datasets has been a challenge for modelling urban flood and managing its risk. A solution is to develop effective approaches to reconstruct high-resolution DEMs from their low-resolution equivalents that are more widely available. However, the current high-resolution DEM reconstruc...
Preprint
div>Our unsupervised clustering technique, VOCCluster, prototyped in Python, handles features of deconvolved GC-MS breath data. VOCCluster was created from a heuristic ontology based on the observation of experts undertaking data processing with a suite of software packages. VOCCluster identifies and clusters groups of volatile organic compounds (V...
Article
In this paper, we propose a novel fully convolutional two-stream fusion network (FCTSFN) for interactiveimage segmentation. The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that predicts the foreground at a reduced resolution, and a multi-scale refining network (MSRN) that refines the foreground at full resol...
Conference Paper
Full-text available
Coordinating multiple agents to complete a set of tasks under time constraints is a complex problem. Distributed consensus-based task allocation algorithms address this problem without the need for human supervision. With such algorithms, agents add tasks to their own schedule according to specified allocation strategies. Various factors, such as t...
Preprint
In this paper, we propose a novel fully convolutional two-stream fusion network (FCTSFN) for interactive image segmentation. The proposed network includes two sub-networks: a two-stream late fusion network (TSLFN) that predicts the foreground at a reduced resolution, and a multi-scale refining network (MSRN) that refines the foreground at full reso...
Conference Paper
In distributed multi-agent task allocation problems, the time to find a solution and a guarantee of reaching a solution, i.e. an execution plan, is critical to ensure a fast response. The problem is made more difficult by time constraints on tasks and on agents, which may prevent some tasks from being executed. This paper proposes a new distributed...
Conference Paper
Full-text available
Unsupervised learning techniques, such as clustering and sparse coding , have been adapted for use with data sets exhibiting nonlinear relationships through the use of kernel machines. These techniques often require an explicit computation of the kernel matrix, which becomes expensive as the number of inputs grows, making it unsuitable for efficien...
Article
Full-text available
This paper considers the problem of maximizing the number of task allocations in a distributed multirobot system under strict time constraints, where other optimization objectives need also be considered. It builds upon existing distributed task allocation algorithms, extending them with a novel method for maximizing the number of task assignments....
Conference Paper
Full-text available
Unsupervised learning permits the development of algorithms that are able to adapt to a variety of different data sets using the same underlying rules thanks to the autonomous discovery of discriminating features during training. Recently, a new class of Hebbian-like and local unsupervised learning rules for neural networks have been developed that...
Conference Paper
Full-text available
Multi-layer models of sparse coding (deep dictionary learning) and dimensionality reduction (PCANet) have shown promise as unsupervised learning models for image classification tasks. However, the pure implementations of these models have limited generalisation capabilities and high computational cost. This work introduces the Deep Hebbian Network...
Article
Full-text available
Biological neural networks are systems of extraordinary computational capabilities shaped by evolution, development, and lifetime learning. The interplay of these elements leads to the emergence of adaptive behavior and intelligence, but the complexity of the whole system of interactions is an obstacle to the understanding of the key factors at pla...
Chapter
Full-text available
Aikido is a Japanese martial art inspired by harmony and intelligent exploitation of human body movements, a consequence of which is believed to be a minimisation of impacts. This study measures the effectiveness of aikido-specific movements to minimise impact forces, and arguably the risk of injuries, in person-to-floor contact. In one experiment,...
Book
This book presents the main scientific results of the 10th International Symposium of Computer Science in Sport (IACSS/ISCSS 2015), sponsored by the International Association of Computer Science in Sport in collaboration with the International Society of Sport Psychology (ISSP), which took place between September 9-11, 2015 at Loughborough, UK. Thi...
Article
Full-text available
Articulated movements are fundamental in many human and robotic tasks. While humans can learn and generalise arbitrarily long sequences of movements, and particularly can optimise them to fit the constraints and features of their body, robots are often programmed to execute point-to-point precise but fixed patterns. This study proposes a new approa...
Conference Paper
Learning in human-robot interaction, as well as in human-to-human situations, is characterised by noisy stimuli, variable timing of stimuli and actions, and delayed rewards. A recent model of neural learning, based on modulated plasticity, suggested the use of rare correlations and eligibility traces to model conditioning in real-world situations w...
Article
Full-text available
Neural conditioning associates cues and actions with following rewards. The environments in which robots operate, however, are pervaded by a variety of disturbing stimuli and uncertain timing. In particular, variable reward delays make it difficult to reconstruct which previous actions are responsible for following rewards. Such an uncertainty is h...
Conference Paper
Learning and reproducing complex movements is an important skill for robots. However, while humans can learn and generalise new complex trajectories, robots are often programmed to execute point-by-point precise but fixed patterns. This study proposes a method for decomposing new complex trajectories into a set of known robot-based primitives. Inst...
Article
Full-text available
Flexible, robust, precise, adaptive, compliant and safe: these are some of the qualities robots must have to interact safely and productively with humans. Yet robots are still nowadays perceived as too rigid, clumsy and not sufficiently adaptive to work efficiently in interaction with people. The AMARSi Project endeavors to design and implement ric...
Conference Paper
Full-text available
Body morphology is thought to have heavily influenced the evolution of neural architecture. However, the extent of this interaction and its underlying principles are largely unclear. To help us elucidate these principles, we examine the artificial evolution of a hypothetical nervous system embedded in a fish-inspired animat. The aim is to observe t...
Article
Full-text available
An agent that deviates from a usual or previous course of action can be said to display novel or varying behaviour. Novelty of behaviour can be seen as the result of real or apparent randomness in decision making, which prevents an agent from repeating exactly past choices. In this paper, novelty of behaviour is considered as an evolutionary precur...
Conference Paper
Full-text available
Artificial Neural Networks for online learning problems are often implemented with synaptic plasticity to achieve adaptive behaviour. A common problem is that the overall learning dynamics are emergent properties strongly dependent on the correct combination of neural architectures, plasticity rules and environmental features. Which complexity in a...
Article
Full-text available
Although the importance of neuromodulation in neural sub-strates has been widely recognised, the computational role, character-istics and advantages of such models in Artificial Neural Networks are mostly unknown. To investigate this issue, here the autonomous emer-gence of neuromodulatory structures is considered by means of artificial evolution i...
Article
Full-text available
Neuromodulation is considered a key fac-tor in learning and memory in biological neu-ral networks. Recent computational mod-els of modulated plasticity have shown in-creased learning capabilities also in artificial neural networks. In this study, a reward-based dynamic scenario is employed to test networks evolved with modulatory dynamics. The anal...
Article
Full-text available
The integration of modulatory neurons into evolutionary artificial neural networks is proposed here. A model of modulatory neurons was devised to describe a plasticity mechanism at the low level of synapses and neurons. No initial assumptions were made on the network structures or on the system level dynamics. The work of this thesis studied the ou...
Conference Paper
Full-text available
Environments with varying reward contingencies constitute a challenge to many living creatures. In such conditions, animals capable of adaptation and learning derive an advantage. Recent studies suggest that neuromodulatory dynamics are a key factor in regulating learning and adaptivity when reward conditions are subject to variability. In biologic...
Article
Full-text available
Conference Paper
Full-text available
This paper describes a new simple operator for Evolutionary Algorithms (EA) to climb ridged landscapes.
Conference Paper
Full-text available
Evolutionary Algorithms (EAs) have been largely applied to optimisation and synthesis of controllers. In spite of several successful applications and competitive solutions, the stochastic nature of EAs and the uncertainty of the results have considerably hindered their use in industrial applications. In this paper we propose a Genetic Algorithm (GA...
Conference Paper
Full-text available
The design of a robust controller for a constrained SISO linear system is considered. Initially, the study of a solution provided by genetic programming (GP) outlined that the GP search process does not achieve time-optimality. A genetic algorithm (GA) was chosen and implemented to confront the performance of the GP solution. The system presented I...
Conference Paper
Full-text available
The design of a robust control system for a specified second order plant is considered using three different approaches. Initially, a con- trol system evolved by a genetic programming algorithm is reproduced and analysed in order to identify its advantages and drawbacks. The au- tomatic design technique is compared to a traditional one through the...
Article
Full-text available
Abstract A comparison between a genetically evolved controlled system and a standard PID controlled system is carried out. In \Method and Appara- tus for Automatic Synthesis Controllers" by John Koza et al., a method for the automatic design and synthesis of controllers by means of ge-
Article
Full-text available
The design of a robust 1 control system is considered using a traditional approach, a genetic programming and a genetic algorithm method. Initially, an existing GP-evolved control system is reproduced and compared to a traditional PID 2 in order to identify its advantages and drawbacks. A set of unspecified control constraints explored by the GP se...

Network

Cited By

Projects

Projects (3)
Project
This project is to model and test a novel design method for wave energy converters based on mathematics and artificial intelligence.
Archived project
Adaptive Modules Architecture for Rich Motor-Skills