Working Memory Networks for Learning Multiple Groupings of Temporarily Ordered Events: Applications to 3-D Visual Object Recognition

Working memory neural networks are characterized which encode the invariant temporal order of sequential events that may be presented at widely differing speeds, durations, and interstimulus intervals. This temporal order code is designed to enable all possible groupings of sequential events to be stably learned and remembered in real time, even as new events perturb the system. Such a competence is needed in neural architectures which self-organize learned codes for variable-rate speech perception, sensory-motor planning, or 3-D visual object recognition. Using such a working memory, a self-organizing architecture for invariant 3-D visual object recognition is described that is based on the model of Seibert and Waxman [1].

ART 2-A: An Adaptive Resonance Algorithm for Rapid Category Learning and Recognition

This article introduces ART 2-A, an efficient algorithm that emulates the self-organizing pattern recognition and hypothesis testing properties of the ART 2 neural network architecture, but at a speed two to three orders of magnitude faster. Analysis and simulations show how the ART 2-A systems correspond to ART 2 dynamics at both the fast-learn limit and at intermediate learning rates. Intermediate learning rates permit fast commitment of category nodes but slow recoding, analogous to properties of word frequency effects, encoding specificity effects, and episodic memory. Better noise tolerance is hereby achieved without a loss of learning stability. The ART 2 and ART 2-A systems are contrasted with the leader algorithm. The speed of ART 2-A makes practical the use of ART 2 modules in large-scale neural computation.

Working Memory Networks for Learning Temporal Order, with Application to 3-D Visual Object Recognition

Working memory neural networks are characterized which encode the invariant temporal order of sequential events. Inputs to the networks, called Sustained Temporal Order REcurrent (STORE) models, may be presented at widely differing speeds, durations, and interstimulus intervals. The STORE temporal order code is designed to enable all emergent groupings of sequential events to be stably learned and remembered in real time, even as new events perturb the system. Such a competence is needed in neural architectures which self-organize learned codes for variable-rate speech perception, sensory-motor planning, or 3-D visual object recognition. Using such a working memory, a self-organizing architecture for invariant 3-D visual object recognition is described. The new model is based on the model of Seibert and Waxman (1990a), which builds a 3-D representation of an object from a temporally ordered sequence of its 2-D aspect graphs. The new model, called an ARTSTORE model, consists of the following cascade of processing modules: Invariant Preprocessor --> ART 2 --> STORE Model --> ART 2 --> Outstar Network.

Fuzzy ART: Fast Stable Learning and Categorization of Analog Patterns by an Adaptive Resonance System

A Fuzzy ART model capable of rapid stable learning of recognition categories in response to arbitrary sequences of analog or binary input patterns is described. Fuzzy ART incorporates computations from fuzzy set theory into the ART 1 neural network, which learns to categorize only binary input patterns. The generalization to learning both analog and binary input patterns is achieved by replacing appearances of the intersection operator (n) in AHT 1 by the MIN operator (Λ) of fuzzy set theory. The MIN operator reduces to the intersection operator in the binary case. Category proliferation is prevented by normalizing input vectors at a preprocessing stage. A normalization procedure called complement coding leads to a symmetric theory in which the MIN operator (Λ) and the MAX operator (v) of fuzzy set theory play complementary roles. Complement coding uses on-cells and off-cells to represent the input pattern, and preserves individual feature amplitudes while normalizing the total on-cell/off-cell vector. Learning is stable because all adaptive weights can only decrease in time. Decreasing weights correspond to increasing sizes of category "boxes". Smaller vigilance values lead to larger category boxes. Learning stops when the input space is covered by boxes. With fast learning and a finite input set of arbitrary size and composition, learning stabilizes after just one presentation of each input pattern. A fast-commit slow-recode option combines fast learning with a forgetting rule that buffers system memory against noise. Using this option, rare events can be rapidly learned, yet previously learned memories are not rapidly erased in response to statistically unreliable input fluctuations.

Fuzzy ARTMAP: A Neural Network Architecture for Incremental Supervised Learning of Analog Multidimensional Maps

A new neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors. The architecture, called Fuzzy ARTMAP, achieves a synthesis of fuzzy logic and Adaptive Resonance Theory (ART) neural networks by exploiting a close formal similarity between the computations of fuzzy subsethood and ART category choice, resonance, and learning. Fuzzy ARTMAP also realizes a new Minimax Learning Rule that conjointly minimizes predictive error and maximizes code compression, or generalization. This is achieved by a match tracking process that increases the ART vigilance parameter by the minimum amount needed to correct a predictive error. As a result, the system automatically learns a minimal number of recognition categories, or "hidden units", to met accuracy criteria. Category proliferation is prevented by normalizing input vectors at a preprocessing stage. A normalization procedure called complement coding leads to a symmetric theory in which the MIN operator (Λ) and the MAX operator (v) of fuzzy logic play complementary roles. Complement coding uses on-cells and off-cells to represent the input pattern, and preserves individual feature amplitudes while normalizing the total on-cell/off-cell vector. Learning is stable because all adaptive weights can only decrease in time. Decreasing weights correspond to increasing sizes of category "boxes". Smaller vigilance values lead to larger category boxes. Improved prediction is achieved by training the system several times using different orderings of the input set. This voting strategy can also be used to assign probability estimates to competing predictions given small, noisy, or incomplete training sets. Four classes of simulations illustrate Fuzzy ARTMAP performance as compared to benchmark back propagation and genetic algorithm systems. These simulations include (i) finding points inside vs. outside a circle; (ii) learning to tell two spirals apart; (iii) incremental approximation of a piecewise continuous function; and (iv) a letter recognition database. The Fuzzy ARTMAP system is also compared to Salzberg's NGE system and to Simpson's FMMC system.

A Neural Network of Adaptively Timed Reinforcement Learning and Hippocampal Dynamics

A neural model is described of how adaptively timed reinforcement learning occurs. The adaptive timing circuit is suggested to exist in the hippocampus, and to involve convergence of dentate granule cells on CA3 pyramidal cells, and NMDA receptors. This circuit forms part of a model neural system for the coordinated control of recognition learning, reinforcement learning, and motor learning, whose properties clarify how an animal can learn to acquire a delayed reward. Behavioral and neural data are summarized in support of each processing stage of the system. The relevant anatomical sites are in thalamus, neocortex, hippocampus, hypothalamus, amygdala, and cerebellum. Cerebellar influences on motor learning are distinguished from hippocampal influences on adaptive timing of reinforcement learning. The model simulates how damage to the hippocampal formation disrupts adaptive timing, eliminates attentional blocking, and causes symptoms of medial temporal amnesia. It suggests how normal acquisition of subcortical emotional conditioning can occur after cortical ablation, even though extinction of emotional conditioning is retarded by cortical ablation. The model simulates how increasing the duration of an unconditioned stimulus increases the amplitude of emotional conditioning, but does not change adaptive timing; and how an increase in the intensity of a conditioned stimulus "speeds up the clock", but an increase in the intensity of an unconditioned stimulus does not. Computer simulations of the model fit parametric conditioning data, including a Weber law property and an inverted U property. Both primary and secondary adaptively timed conditioning are simulated, as are data concerning conditioning using multiple interstimulus intervals (ISIs), gradually or abruptly changing ISis, partial reinforcement, and multiple stimuli that lead to time-averaging of responses. Neurobiologically testable predictions are made to facilitate further tests of the model.

Adaptive Resonance Associative Map: A Hierarchical ART System for Fast Stable Associative Learning

This paper introduces a new class of predictive ART architectures, called Adaptive Resonance Associative Map (ARAM) which performs rapid, yet stable heteroassociative learning in real time environment. ARAM can be visualized as two ART modules sharing a single recognition code layer. The unit for recruiting a recognition code is a pattern pair. Code stabilization is ensured by restricting coding to states where resonances are reached in both modules. Simulation results have shown that ARAM is capable of self-stabilizing association of arbitrary pattern pairs of arbitrary complexity appearing in arbitrary sequence by fast learning in real time environment. Due to the symmetrical network structure, associative recall can be performed in both directions.

Normal and Amnesis Learning, Recognition, and Memory by a Neural Model of Cortico-Hippocampal Interactions

The processes by which humans and other primates learn to recognize objects have been the subject of many models. Processes such as learning, categorization, attention, memory search, expectation, and novelty detection work together at different stages to realize object recognition. In this article, Gail Carpenter and Stephen Grossberg describe one such model class (Adaptive Resonance Theory, ART) and discuss how its structure and function might relate to known neurological learning and memory processes, such as how inferotemporal cortex can recognize both specialized and abstract information, and how medial temporal amnesia may be caused by lesions in the hippocampal formation. The model also suggests how hippocampal and inferotemporal processing may be linked during recognition learning.

Artefact detection and removal algorithms for EEG diagnostic systems

The electroencephalogram (EEG) is a medical technology that is used in the monitoring of the brain and in the diagnosis of many neurological illnesses. Although coarse in its precision, the EEG is a non-invasive tool that requires minimal set-up times, and is suitably unobtrusive and mobile to allow continuous monitoring of the patient, either in clinical or domestic environments. Consequently, the EEG is the current tool-of-choice with which to continuously monitor the brain where temporal resolution, ease-of- use and mobility are important. Traditionally, EEG data are examined by a trained clinician who identifies neurological events of interest. However, recent advances in signal processing and machine learning techniques have allowed the automated detection of neurological events for many medical applications. In doing so, the burden of work on the clinician has been significantly reduced, improving the response time to illness, and allowing the relevant medical treatment to be administered within minutes rather than hours. However, as typical EEG signals are of the order of microvolts (μV ), contamination by signals arising from sources other than the brain is frequent. These extra-cerebral sources, known as artefacts, can significantly distort the EEG signal, making its interpretation difficult, and can dramatically disimprove automatic neurological event detection classification performance. This thesis therefore, contributes to the further improvement of auto- mated neurological event detection systems, by identifying some of the major obstacles in deploying these EEG systems in ambulatory and clinical environments so that the EEG technologies can emerge from the laboratory towards real-world settings, where they can have a real-impact on the lives of patients. In this context, the thesis tackles three major problems in EEG monitoring, namely: (i) the problem of head-movement artefacts in ambulatory EEG, (ii) the high numbers of false detections in state-of-the-art, automated, epileptiform activity detection systems and (iii) false detections in state-of-the-art, automated neonatal seizure detection systems. To accomplish this, the thesis employs a wide range of statistical, signal processing and machine learning techniques drawn from mathematics, engineering and computer science. The first body of work outlined in this thesis proposes a system to automatically detect head-movement artefacts in ambulatory EEG and utilises supervised machine learning classifiers to do so. The resulting head-movement artefact detection system is the first of its kind and offers accurate detection of head-movement artefacts in ambulatory EEG. Subsequently, addtional physiological signals, in the form of gyroscopes, are used to detect head-movements and in doing so, bring additional information to the head- movement artefact detection task. A framework for combining EEG and gyroscope signals is then developed, offering improved head-movement arte- fact detection. The artefact detection methods developed for ambulatory EEG are subsequently adapted for use in an automated epileptiform activity detection system. Information from support vector machines classifiers used to detect epileptiform activity is fused with information from artefact-specific detection classifiers in order to significantly reduce the number of false detections in the epileptiform activity detection system. By this means, epileptiform activity detection which compares favourably with other state-of-the-art systems is achieved. Finally, the problem of false detections in automated neonatal seizure detection is approached in an alternative manner; blind source separation techniques, complimented with information from additional physiological signals are used to remove respiration artefact from the EEG. In utilising these methods, some encouraging advances have been made in detecting and removing respiration artefacts from the neonatal EEG, and in doing so, the performance of the underlying diagnostic technology is improved, bringing its deployment in the real-world, clinical domain one step closer.

A critical realist examination of the inhibitors of double loop learning in an agile adoption

The original solution to the high failure rate of software development projects was the imposition of an engineering approach to software development, with processes aimed at providing a repeatable structure to maintain a consistency in the ‘production process’. Despite these attempts at addressing the crisis in software development, others have argued that the rigid processes of an engineering approach did not provide the solution. The Agile approach to software development strives to change how software is developed. It does this primarily by relying on empowered teams of developers who are trusted to manage the necessary tasks, and who accept that change is a necessary part of a development project. The use of, and interest in, Agile methods in software development projects has expanded greatly, yet this has been predominantly practitioner driven. There is a paucity of scientific research on Agile methods and how they are adopted and managed. This study aims at addressing this paucity by examining the adoption of Agile through a theoretical lens. The lens used in this research is that of double loop learning theory. The behaviours required in an Agile team are the same behaviours required in double loop learning; therefore, a transition to double loop learning is required for a successful Agile adoption. The theory of triple loop learning highlights that power factors (or power mechanisms in this research) can inhibit the attainment of double loop learning. This study identifies the negative behaviours - potential power mechanisms - that can inhibit the double loop learning inherent in an Agile adoption, to determine how the Agile processes and behaviours can create these power mechanisms, and how these power mechanisms impact on double loop learning and the Agile adoption. This is a critical realist study, which acknowledges that the real world is a complex one, hierarchically structured into layers. An a priori framework is created to represent these layers, which are categorised as: the Agile context, the power mechanisms, and double loop learning. The aim of the framework is to explain how the Agile processes and behaviours, through the teams of developers and project managers, can ultimately impact on the double loop learning behaviours required in an Agile adoption. Four case studies provide further refinement to the framework, with changes required due to observations which were often different to what existing literature would have predicted. The study concludes by explaining how the teams of developers, the individual developers, and the project managers, working with the Agile processes and required behaviours, can inhibit the double loop learning required in an Agile adoption. A solution is then proposed to mitigate these negative impacts. Additionally, two new research processes are introduced to add to the Information Systems research toolkit.

Molecular mapping of movement-associated areas in the avian brain: a motor theory for vocal learning origin.

Vocal learning is a critical behavioral substrate for spoken human language. It is a rare trait found in three distantly related groups of birds-songbirds, hummingbirds, and parrots. These avian groups have remarkably similar systems of cerebral vocal nuclei for the control of learned vocalizations that are not found in their more closely related vocal non-learning relatives. These findings led to the hypothesis that brain pathways for vocal learning in different groups evolved independently from a common ancestor but under pre-existing constraints. Here, we suggest one constraint, a pre-existing system for movement control. Using behavioral molecular mapping, we discovered that in songbirds, parrots, and hummingbirds, all cerebral vocal learning nuclei are adjacent to discrete brain areas active during limb and body movements. Similar to the relationships between vocal nuclei activation and singing, activation in the adjacent areas correlated with the amount of movement performed and was independent of auditory and visual input. These same movement-associated brain areas were also present in female songbirds that do not learn vocalizations and have atrophied cerebral vocal nuclei, and in ring doves that are vocal non-learners and do not have cerebral vocal nuclei. A compilation of previous neural tracing experiments in songbirds suggests that the movement-associated areas are connected in a network that is in parallel with the adjacent vocal learning system. This study is the first global mapping that we are aware for movement-associated areas of the avian cerebrum and it indicates that brain systems that control vocal learning in distantly related birds are directly adjacent to brain systems involved in movement control. Based upon these findings, we propose a motor theory for the origin of vocal learning, this being that the brain areas specialized for vocal learning in vocal learners evolved as a specialization of a pre-existing motor pathway that controls movement.

Teaching, learning and assessment in MSc. Databases units at University of Greenwich

In this paper we look at ways of delivering and assessing learning on database units offered on higher degree programmes (MSc) in the School of Computing and Mathematical Sciences at the University of Greenwich. Of critical importance is the teaching methods employed for verbal disposition, practical laboratory exercises and a careful evaluation of assessment methods and assessment tools in view of the fact that databases involve not only database design but also use of practical tools, such as database management systems (DBMSs) software, human designers, database administrators (DBA) and end users. Our goal is to clearly identify potential key success factors in delivering and assessing learning in both practical and theoretical aspects of database course units.

Personalised e-learning, semantic web and learning ontologies

Kurzel(2004) points out that researchers in e-learning and educational technologists, in a quest to provide improved Learning Environments (LE) for students are focusing on personalising the experience through a Learning Management System (LMS) that attempts to tailor the LE to the individual (see amongst others Eklund & Brusilovsky, 1998; Kurzel, Slay, & Hagenus, 2003; Martinez,2000; Sampson, Karagiannidis, & Kinshuk, 2002; Voigt & Swatman; 2003). According to Kurzel (2004) this tailoring can have an impact on content and how it’s accessed; the media forms used; method of instruction employed and the learning styles supported. This project is aiming to move personalisation forward to the next generation, by tackling the issue of Personalised e-Learning platforms as pre-requisites for building and generating individualised learning solutions. The proposed development is to create an e-learning platform with personalisation built-in. This personalisation is proposed to be set from different levels of within the system starting from being guided by the information that the user inputs into the system down to the lower level of being set using information inferred by the system’s processing engine. This paper will discuss some of our early work and ideas.

Reaching across organisational, sectoral and geographical boundaries: exploring the learning potential of an EU cross-border project

Research This paper outlines some of the key findings from an evaluation of the project and demonstrates that EC funded projects such as this, which seek to promote cross border collaboration and understanding (i.e. across organisational, sectoral and geographical boundaries) offer considerable learning potential – not least about variances in health politics across different communities. However, for this learning to be realised a comprehensive system of knowledge management needs to be an integral part of project planning alongside a system for sustaining embryonic professional networks. The concept of managing relationships was also a key part of the projects success. Executing a project funded by the EU demands the development of complex organisational skills to negotiate all the administrative challenges en route to successful completion and this project in particular relied for its success on the development of social relationships of trust and mutual respect across national, professional and social boundaries. Context A three–year European Commission funded project designed to exchange a wide range of staff (professional semiprofessional and voluntary staff in health and social care) project led by the University of Greenwich (UK) and the Université Catholique de Lille, France was completed this year (February 2008). The project was complex because it involved working in different national contexts, was multi-disciplinary, and demanded the negotiation of multiple boundaries. Theories A mixed method evaluation including written reports gathered immediately after each exchange visit and a post hoc series of individual interviews and focus groups was conducted in order to gain qualitative information (from the participants perspective) on their experiences and to identify any learning gained. Results Analysis of the data provided evidence of learning on a number of levels; personally, inter and intra professionally and organisationally as well as across sectors and also from a project management perspective. The learning crystallised around the extent of the differences noted by the participants between the UK and the French health and social care systems despite geographical proximity, common membership of the EU and many shared challenges in health and social care. The extent of these differences, noted at every level from policy to practice proved a rich source for reflection on organisational philosophies, ways of working, distribution of resources, professional roles and autonomy and professional registration and mobility - in short on health politics at ‘macro’ and ‘micro’ levels.

Bridging the gap with teamwork: collaborative leadership for communities of practice in the learning and skills sector

Collaborative approaches in leadership and management are increasingly acknowledged to play a key role in successful institutions in the learning and skills sector (LSS) (Ofsted, 2004). Such approaches may be important in bridging the potential 'distance' (psychological, cultural, interactional and geographical) (Collinson, 2005) that may exist between 'leaders' and 'followers', fostering more democratic communal solidarity. This paper reports on a 2006-07 research project funded by the Centre for Excellence in Leadership (CEL) that aimed to collect and analyse data on 'collaborative leadership' (CL) in the learning and skills sector. The project investigated collaborative leadership and its potential for benefiting staff through trust and knowledge-sharing in communities of practice (CoPs). The project forms part of longer-term educational research investigating leadership in a collaborative inquiry process (Jameson et al., 2006). The research examined the potential for CL to benefit institutions, analysing respondents' understanding of and resistance to collaborative practices. Quantitative and qualitative data from senior managers and lecturers was analysed using electronic data in SPSS and Tropes Zoom. The project aimed to recommend systems and practices for more inclusive, diverse leadership (Lumby et al., 2005). Collaborative leadership has increasingly gained international prominence as emphasis shifted towards team leadership beyond zero-sum 'leadership'/ 'followership' polarities into more mature conceptions of shared leadership spaces, within which synergistic leadership spaces can be mediated. The relevance of collaboration within the LSS has been highlighted following a spate of recent government-driven policy developments in FE. The promotion of CL addresses concerns about the apparent 'remoteness' of some senior managers, and the 'neo-management' control of professionals which can increase 'distance' between leaders and 'followers' and may de-professionalise staff in an already disempowered sector. Positive benefit from 'collaborative advantage' tends to be assumed in idealistic interpretations of CL, but potential 'collaborative inertia' may be problematic in a sector characterised by rapid top-down policy changes and continuous external audit and surveillance. Constant pressure for achievement against goals leaves little time for democratic group negotiations, despite the desires of leaders to create a more collaborative ethos. Yet prior models of intentional communities of practice potentially offer promise for CL practice to improve group performance despite multiple constraints. The CAMEL CoP model (JISC infoNet, 2006) was linked to the project, providing one practical way of implementing CL within situated professional networks.The project found that a good understanding of CL was demonstrated by most respondents, who thought it could enable staff to share power and work in partnership to build trust and conjoin skills, abilities and experience to achieve common goals for the good of the sector. However, although most respondents expressed agreement with the concept and ideals of CL, many thought this was currently an idealistically democratic, unachievable pipe dream in the LSS. Many respondents expressed concerns with the 'audit culture' and authoritarian management structures in FE. While there was a strong desire to see greater levels of implementation of CL, and 'collaborative advantage' from the 'knowledge sharing benefit potential' of team leadership, respondents also strongly advised against the pitfalls of 'collaborative inertia'. A 'distance' between senior leadership views and those of staff lower down the hierarchy regarding aspects of leadership performance in the sector was reported. Finally, the project found that more research is needed to investigate CL and develop innovative methods of practical implementation within autonomous communities of professional practice.