E. Alonso

E. Alonso
City, University of London · Department of Computer Science

PhD

About

147
Publications
19,449
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
1,398
Citations
Additional affiliations
January 2006 - December 2013
Centre for Computational and Animal Learning Research
Centre for Computational and Animal Learning Research
Position
  • Co-director
June 2001 - present
City, University of London
Position
  • Professor (Full)
January 1996 - June 2001

Publications

Publications (147)
Preprint
Full-text available
Recent deep reinforcement learning (DRL) successes rely on end-to-end learning from fixed-size observational inputs (e.g. image, state-variables). However, many challenging and interesting problems in decision making involve observations or intermediary representations which are best described as a set of entities: either the image-based approach w...
Article
Full-text available
This paper introduces a computational model of creative problem-solving in deep reinforcement learning agents, inspired by cognitive theories of creativity. The AIGenC model aims at enabling artificial agents to learn, use and generate transferable representations. AIGenC is embedded in a deep learning architecture that includes three main componen...
Preprint
Full-text available
This paper introduces a computational model of creative problem-solving in deep reinforcement learning agents, inspired by cognitive theories of creativity. The AIGenC model aims at enabling artificial agents to learn, use and generate transferable representations. AIGenC is embedded in a deep learning architecture that includes three main componen...
Chapter
Full-text available
In this paper we introduce Local Logo Generative Adversarial Network (LL-GAN) that uses regional features extracted from Faster R-CNN for logo generation. We demonstrate the strength of this approach by training the framework on a small style-rich dataset of real heavy metal logos to generate new ones. LL-GAN achieves Inception Score of 5.29 and Fr...
Article
This article investigates the local stability and local convergence of a class of neural network (NN) controllers with error integrals as inputs for reference tracking. It is formally proved that if the input of the NN controller consists exclusively of error terms, the control system shows a non-zero steady-state error for any constant reference e...
Preprint
Full-text available
In this paper we introduce the Local Logo Generative Adversarial Network (LL-GAN) that uses regional features extracted from the Faster Regional Convolutional Neural Network (Faster R-CNN) to generate logos. We demonstrate the strength of this approach by training the framework on a small style-rich dataset collected online to generate large impres...
Article
With increasing concerns of climate change, renewable resources such as photovoltaic (PV) have gained popularity as a means of energy generation. The smooth integration of such resources in power system operations is enabled by accurate forecasting mechanisms that address their inherent intermittency and variability. This paper proposes a novel pro...
Article
Full-text available
Abstract The rise of microgrid‐based architectures is modifying significantly the energy control landscape in distribution systems, making distributed control mechanisms necessary to ensure reliable power system operations. In this article, the use of Reinforcement Learning techniques is proposed to implement load frequency control (LFC) without re...
Article
Full-text available
This paper investigates the classification of radiographic images with eleven convolutional neural network (CNN) architectures (GoogleNet, VGG-19, AlexNet, SqueezeNet, ResNet-18, Inception-v3, ResNet-50, VGG-16, ResNet-101, DenseNet-201 and Inception-ResNet-v2). The CNNs were used to classify a series of wrist radiographs from the Stanford Musculos...
Article
Full-text available
The incorporation of renewable energy into power systems poses serious challenges to the transmission and distribution power system operators (TSOs and DSOs). To fully leverage these resources there is a need for a new market design with improved coordination between TSOs and DSOs. In this paper we propose two coordination schemes between TSOs and...
Conference Paper
Full-text available
Multi-agent reinforcement learning in mixed-motive settings allows for the study of complex dynamics of agent interactions. Embodied agents in partially observable environments with the ability to communicate can share information, agree on strategies, or even lie to each other. In order to study this, we propose a simple environment where we can i...
Preprint
Full-text available
This paper investigates the classification of radiographic images with eleven convolutional neural network (CNN) architectures (GoogleNet, VGG-19, AlexNet, SqueezeNet, ResNet-18, Inception-v3, ResNet-50, VGG-16, ResNet-101, DenseNet-201 and Inception-ResNet-v2). The CNNs were used to classify a series of wrist radiographs from the Stanford Musculos...
Preprint
Full-text available
The incorporation of renewable energy into power systems poses serious challenges to the transmission and distribution power system operators (TSOs and DSOs). To fully leverage these resources there is a need for a new market design with improved coordination between TSOs and DSOs. In this paper we propose two coordination schemes between TSOs and...
Article
This paper aims to bridge this gap between neuro-symbolic learning (NSL) and graph neural networks (GNN) approaches and provide a comparative study. We argue that the natural evolution of NSL leads to GNNs, while the logic programming foundations of NSL can bring powerful tools to improve the way information is represented and pre-processed for the...
Preprint
The rise of microgrid-based architectures is heavily modifying the energy control landscape in distribution systems making distributed control mechanisms necessary to ensure reliable power system operations. In this paper, we propose the use of Reinforcement Learning techniques to implement load frequency control without requiring a central authori...
Article
Full-text available
Rewards act as a motivator for positive behavior and learning. Although compounding evidence indicates that reward processing operates differently in autistic individuals who do not have co‐occurring learning disabilities, little is known about individuals who have such difficulties or other complex needs. This study aimed first to assess the feasi...
Preprint
Full-text available
With increasing concerns of climate change, renewable resources such as photovoltaic (PV) have gained popularity as a means of energy generation. The smooth integration of such resources in power system operations is enabled by accurate forecasting mechanisms that address their inherent intermittency and variability. This paper proposes a probabili...
Article
Background: Resting state fMRI has emerged as a popular neuroimaging method for automated recognition and classification of brain disorders. Attention Deficit Hyperactivity Disorder (ADHD) is one of the most common brain disorders affecting young children, yet its underlying mechanism is not completely understood and its diagnosis is mainly depend...
Article
The introduction of new technologies and increased penetration of renewable resources is altering the power distribution landscape which now includes a larger number of micro-generators. The centralized strategies currently employed for performing frequency control in a cost efficient way need to be revisited and decentralized to conform with the i...
Article
The multi-population replicator dynamics is a dynamic approach to coevolving populations and multi-player games and is related to Cross learning. In general, not every equilibrium is a Nash equilibrium of the underlying game, and the convergence is not guaranteed. In particular, no interior equilibrium can be asymptotically stable in the multi-popu...
Article
Full-text available
Traditionally, fault diagnosis in telecommunication network management is carried out by humans who use software support systems. The phenomenal growth in telecommunication networks has nonetheless triggered the interest in more autonomous approaches, capable of coping with emergent challenges such as the need to diagnose faults’ root causes under...
Preprint
The multi-population replicator dynamics (RD) can be considered a dynamic approach to the study of multi-player games, where it was shown to be related to Cross' learning, as well as of systems of coevolving populations. However, not all of its equilibria are Nash equilibria (NE) of the underlying game, and neither convergence to an NE nor converge...
Article
Full-text available
In this article a formal model of associative learning is presented that incorporates representational and computational mechanisms that, as a coherent corpus, empower it to make accurate predictions of a wide variety of phenomena that, so far, have eluded a unified account in learning theory. In particular, the Double Error Dynamic Asymptote (DDA)...
Article
This paper focuses on current control in a permanent-magnet synchronous motor (PMSM). This paper has two main objectives: the first objective is to develop a neural-network (NN) vector controller to overcome the decoupling inaccuracy problem associated with the conventional proportional-integral-based vector-control methods. The NN is developed usi...
Preprint
Full-text available
In this paper a formal model of associative learning is presented which incorporates representational and computational mechanisms that, as a coherent corpus, empower it to make accurate predictions of a wide variety of phenomena that so far have eluded a unified account in learning theory. In particular, the Double Error Dynamic Asymptote (DDA) mo...
Chapter
Magnetic Resonance Spectroscopy (MRS) provides valuable information to help with the identification and understanding of brain tumors, yet MRS is not a widely available medical imaging modality. Aiming to counter this issue, this research draws on the advancements in machine learning techniques in other fields for the generation of artificial data....
Preprint
Full-text available
Magnetic Resonance Spectroscopy (MRS) provides valuable information to help with the identification and understanding of brain tumors, yet MRS is not a widely available medical imaging modality. Aiming to counter this issue, this research draws on the advancements in machine learning techniques in other fields for the generation of artificial data....
Article
Deep Reinforcement Learning (deep RL) has made several breakthroughs in recent years in applications ranging from complex control tasks in unmanned vehicles to game playing. Despite their success, deep RL still lacks several important capacities of human intelligence, such as transfer learning, abstraction and interpretability. Deep Symbolic Reinfo...
Article
The main goal of this study is the development of an aggregate air itinerary market share model. In order to achieve this, multinomial logit models are applied to distribute the city-pair passenger demand across the available itineraries. The models are developed at an aggregate level using open-source booking data for a large group of city-pairs w...
Article
Full-text available
Computational models of classical conditioning have made significant contributions to the theoretic understanding of associative learning, yet they still struggle when the temporal aspects of conditioning are taken into account. Interval timing models have contributed a rich variety of time representations and provided accurate predictions for the...
Preprint
Full-text available
In this paper a formal model of associative learning is presented which incorporates representational and computational mechanisms that, as a coherent corpus, empower it to make accurate predictions of a wide variety of phenomena that so far have eluded a unified account in learning theory. In particular, the Double Error model introduces: 1) a ful...
Article
Resting state fMRI has emerged as a popular neuroimaging method for automated recognition and classification of different brain disorders. Attention Deficit Hyperactivity Disorder (ADHD) is one of the most common brain disorders affecting young children, yet its underlying mechanism is not completely understood and its diagnosis is mainly dependent...
Conference Paper
Full-text available
Investigation of functional brain connectivity patterns using functional MRI has received significant interest in the neuroimaging domain. Brain functional connectivity alterations have widely been exploited for diagnosis and prediction of various brain disorders. Over the last several years, the research community has made tremendous advancements...
Article
Exploring and making predictions based on single-molecule data can be challenging, not only due to the sheer size of the datasets, but also because a priori knowledge about the signal characteristics is typically limited and poor signal-to-noise ratio. For example, hypothesis-driven data exploration, informed by an expectation of the signal charact...
Article
Full-text available
Conditioning, how animals learn to associate two or more events, is one of the most influential paradigms in learning theory. It is nevertheless unclear how current models of associative learning can accommodate complex phenomena without ad hoc representational assumptions. We propose to embrace deep neural networks to negotiate this problem.
Article
Full-text available
Drift-diffusion models (DDMs) are a popular framework for explaining response times in decision-making tasks. Recently, the DDM architecture has been used to model interval timing. The Time-adaptive DDM (TDDM) is a physiologically plausible mechanism that adapts in real-time to different time intervals while preserving timescale invariance. One key...
Research
Full-text available
Book of Abstracts of the First Workshop on Computational Modelling of Classical Conditioning. CoMoCC, London 2016
Conference Paper
Full-text available
Attention Deficit Hyperactive Disorder (ADHD) is one of the most common disorders affecting young children, and its underlying mechanism is not completely understood. This paper proposes a phenotypic integrated machine learning framework to investigate functional connectivity alterations between ADHD and control subjects not diagnosed with ADHD, em...
Technical Report
Full-text available
This report introduces a formal comparison between Hall and Rodríguez’s elaboration of the Pearce and Hall model and the original. It shows mathematically and with a set of simulations that with a provision to set an initial excitatory value in Pearce and Hall’s algorithm, both models are equivalent in structure and that they result in identical pr...
Conference Paper
The application of high-voltage dc (HVDC) using voltage-source converters (VSC) has surged recently in electric power transmission and distribution systems. An optimal vector control of a VSC-HVDC system which uses an artificial neural network to implement an approximate dynamic programming algorithm and is trained with Levenberg-Marquardt is intro...
Article
Whether animals behave optimally is an open question of great importance, both theoretically and in practice. Attempts to answer this question focus on two aspects of the optimization problem, the quantity to be optimized and the optimization process itself. In this paper, we assume the abstract concept of cost as the quantity to be minimized and p...
Conference Paper
The main goal of the study centers on developing a model for the purpose of air traffic forecasting by using off-the-shelf data mining and machine learning techniques. Although data driven modeling has been extensively applied in the aviation sector, little research has been done in the area of air traffic forecasting. This study is inspired by pre...
Article
This paper investigates how to train a recurrent neural network (RNN) using the Levenberg-Marquardt (LM) algorithm as well as how to implement optimal control of a grid-connected converter (GCC) using an RNN. To successfully and efficiently train an RNN using the LM algorithm, a new forward accumulation through time (FATT) algorithm is proposed to...
Article
In adaptive dynamic programming, neurocontrol, and reinforcement learning, the objective is for an agent to learn to choose actions so as to minimize a total cost function. In this paper, we show that when discretized time is used to model the motion of the agent, it can be very important to do clipping on the motion of the agent in the final time...
Article
Full-text available
This paper presents a novel representational framework for the Temporal Difference (TD) model of learning, which allows the computation of configural stimuli – cumulative compounds of stimuli that generate perceptual emergents known as configural cues. This Simultaneous and Serial Configural-cue Compound Stimuli Temporal Difference model (SSCC TD)...
Article
Three-phase grid-connected converters are widely used in renewable and electric power system applications. Traditionally, grid-connected converters are controlled with standard decoupled d-q vector control mechanisms. However, recent studies indicate that such mechanisms show limitations in their applicability to dynamic systems. This paper investi...
Article
Full-text available
The last 50 years have seen the progressive refinement of our understanding of the mechanisms of classical conditioning and this has resulted in the development of several influential theories that are able to explain with considerable precision a wide variety of experimental findings, and to make non-intuitive predictions that have been confirmed....
Article
The majority of species are under predatory risk in their natural habitat and targeted by predators as part of the food web. During the evolution of ecosystems, manifold mechanisms have emerged to avoid predation. So called secondary defences, which are used after a predator has initiated prey-catching behaviour, commonly involve the expression of...
Article
Full-text available
Classical conditioning is a fundamental paradigm in the study of learning and thus in understanding cognitive processes and behaviour, for which we need comprehensive and accurate models. This paper aims at evaluating and comparing a collection of influential computational models of classical conditioning by analysing the models themselves and agai...
Article
Full-text available
An implicit assumption in the study of operant conditioning and reinforcement learning is that behavior is stochastic, in that it depends on the probability that an outcome follows a response and on how the presence or absence of the output affects the frequency of the response. In this paper we argue that classical probability is not the right too...
Article
We consider the adaptive dynamic programming technique called Dual Heuristic Programming (DHP), which is designed to learn a critic function, when using learned model functions of the environment. DHP is designed for optimizing control problems in large and continuous state spaces. We extend DHP into a new algorithm that we call Value-Gradient Lear...
Conference Paper
The paper provides a first attempt to formalize Systems of Systems based on game theory and Multi-Agent Systems. We propose to use control agents to enforce joint strategies, which solve problems arising from the unconstrained interaction of autonomous agents and where Nash equilibria are sub optimal. In essence, in the resulting systems new soluti...
Article
We present a recurrent neural-network (RNN) controller designed to solve the tracking problem for control systems. We demonstrate that a major difficulty in training any RNN is the problem of exploding gradients, and we propose a solution to this in the case of tracking problems, by introducing a stabilization matrix and by using carefully constrai...
Article
An experience-based aversive learning model of foraging behaviour in uncertain environments is presented. We use Q-learning as a model-free implementation of Temporal Difference learning motivated by growing evidence for neural correlates in natural reinforcement settings. The predator has the choice of including an aposematic prey in its diet or t...
Conference Paper
With the improvement of battery technology over the past two decades and automotive technology advances, more and more vehicle manufacturers have joined in the race to produce new generation of affordable, high-performance Electric Drive Vehicles (EDVs). Permanent Magnet Synchronous Motors (PMSMs) are at the top of AC motors in high performance dri...
Article
Full-text available
In four experiments rats were conditioned to an auditory conditioned stimulus (conditioned stimulus; CS) that was paired with food, and learning about the CS was compared across two conditions in which the mean duration of the CS was equated. In one, the CS was of a single, fixed duration on every trial, and in the other the CS duration was drawn f...
Conference Paper
In this paper we propose an algebraic model of systems based on the concept of symmetry that can be instrumental in representing Systems of Systems two main characteristics, namely complexity and (hierarchical) emergence.