ART-EMAP: A Neural Network Architecture for Learning and Prediction by Evidence Accumulation

This paper introduces ART-EMAP, a neural architecture that uses spatial and temporal evidence accumulation to extend the capabilities of fuzzy ARTMAP. ART-EMAP combines supervised and unsupervised learning and a medium-term memory process to accomplish stable pattern category recognition in a noisy input environment. The ART-EMAP system features (i) distributed pattern registration at a view category field; (ii) a decision criterion for mapping between view and object categories which can delay categorization of ambiguous objects and trigger an evidence accumulation process when faced with a low confidence prediction; (iii) a process that accumulates evidence at a medium-term memory (MTM) field; and (iv) an unsupervised learning algorithm to fine-tune performance after a limited initial period of supervised network training. ART-EMAP dynamics are illustrated with a benchmark simulation example. Applications include 3-D object recognition from a series of ambiguous 2-D views.

Sequential Memory with ART: A Self-Organizing Network Capable of Learning Sequences of Patterns

A model which extends the adaptive resonance theory model to sequential memory is presented. This new model learns sequences of events and recalls a sequence when presented with parts of the sequence. A sequence can have repeated events and different sequences can share events. The ART model is modified by creating interconnected sublayers within ART's F2 layer. Nodes within F2 learn temporal patterns by forming recency gradients within LTM. Versions of the ART model like ART I, ART 2, and fuzzy ART can be used.

A Distributed Outstar Network for Spatial Pattern Learning

The distributed outstar, a generalization of the outstar neural network for spatial pattern learning, is introduced. In the outstar, signals from a source node cause weights to learn and recall arbitrary patterns across a target field of nodes. The distributed outstar replaces the outstar source node with a source field of arbitrarily many nodes, whose activity pattern may be arbitrarily distributed or compressed. Learning proceeds according to a principle of atrophy due to disuse, whereby a path weight decreases in joint proportion to the transmitted path signal and the degree of disuse of the target node. During learning, the total signal to a target node converges toward that node's activity level. Weight changes at a node are apportioned according to the distributed pattern of converging signals. Three synaptic transmission functions, by a product rule, a capacity rule, and a threshold rule, are examined for this system. The three rules are computationally equivalent when source field activity is maximally compressed, or winner-take-all. When source field activity is distributed, catastrophic forgetting may occur. Only the threshold rule solves this problem. Analysis of spatial pattern learning by distributed codes thereby leads to the conjecture that the unit of long-term memory in such a system is an adaptive threshold, rather than the multiplicative path weight widely used in neural models.

A Neural Network Architecture for Autonomous Learning, Recognition, and Prediction in a Nonstationary World

In a constantly changing world, humans are adapted to alternate routinely between attending to familiar objects and testing hypotheses about novel ones. We can rapidly learn to recognize and narne novel objects without unselectively disrupting our memories of familiar ones. We can notice fine details that differentiate nearly identical objects and generalize across broad classes of dissimilar objects. This chapter describes a class of self-organizing neural network architectures--called ARTMAP-- that are capable of fast, yet stable, on-line recognition learning, hypothesis testing, and naming in response to an arbitrary stream of input patterns (Carpenter, Grossberg, Markuzon, Reynolds, and Rosen, 1992; Carpenter, Grossberg, and Reynolds, 1991). The intrinsic stability of ARTMAP allows the system to learn incrementally for an unlimited period of time. System stability properties can be traced to the structure of its learned memories, which encode clusters of attended features into its recognition categories, rather than slow averages of category inputs. The level of detail in the learned attentional focus is determined moment-by-moment, depending on predictive success: an error due to over-generalization automatically focuses attention on additional input details enough of which are learned in a new recognition category so that the predictive error will not be repeated. An ARTMAP system creates an evolving map between a variable number of learned categories that compress one feature space (e.g., visual features) to learned categories of another feature space (e.g., auditory features). Input vectors can be either binary or analog. Computational properties of the networks enable them to perform significantly better in benchmark studies than alternative machine learning, genetic algorithm, or neural network models. Some of the critical problems that challenge and constrain any such autonomous learning system will next be illustrated. Design principles that work together to solve these problems are then outlined. These principles are realized in the ARTMAP architecture, which is specified as an algorithm. Finally, ARTMAP dynamics are illustrated by means of a series of benchmark simulations.

A Network for Learning Kinematics with Application to Human Reaching Models

A model for self-organization of the coordinate transformations required for spatial reaching is presented. During a motor babbling phase, a mapping from spatial coordinate directions to joint motion directions is learned. After learning, the model is able to produce straight-line spatial velocity trajectories with characteristic bell-shaped spatial velocity profiles, as observed in human reaches. Simulation results are presented for transverse plane reaching using a two degree-of-freedom arm.

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.

The differences in the social competence of children who attend integrated junior infant classes and children who attend segregated learning environments

There are a number of reasons why this researcher has decided to undertake this study into the differences in the social competence of children who attend integrated Junior Infant classes and children who attend segregated learning environments. Theses reasons are both personal and professional. My personal reasons stem from having grown up in a family which included both an aunt who presented with Down Syndrome and an uncle who presented with hearing impairment. Both of these relatives' experiences in our education system are interesting. My aunt was considered ineducable while her brother - my uncle - was sent to Dublin (from Cork) at six years of age to be educated by a religious order. My professional reasons, on the other hand, stemmed from my teaching experience. Having taught in both special and integrated classrooms it became evident to me that there was somewhat 'suspicion' attached to integration. Parents of children without disabilities questioned whether this process would have a negative impact on their children's education. While parents of children with disabilities debated whether integrated settings met the specific needs of their children. On the other hand, I always questioned whether integration and inclusiveness meant the same thing. My research has enabled me to find many answers. Increasingly, children with special educational needs (SEN) are attending a variety of integrated and inclusive childcare and education settings. This contemporary practice of educating children who present with disabilities in mainstream classrooms has stimulated vast interest on the impact of such practices on children with identified disabilities. Indeed, children who present with disabilities "fare far better in mainstream education than in special schools" (Buckley, cited in Siggins, 2001,p.25). However, educators and practitioners in the field of early years education and care are concerned with meeting the needs of all children in their learning environments, while also upholding high academic standards (Putman, 1993). Fundamentally, therefore, integrated education must also produce questions about the impact of this practice on children without identified special educational needs. While these questions can be addressed from the various areas of child development (i.e. cognitive, physical, linguistic, emotional, moral, spiritual and creative), this research focused on the social domain. It investigates the development of social competence in junior infant class children without identified disabilities as they experience different educational settings.

Exploring the relationship between social network sites and the consumption of cultural goods through the lens of affordances

This thesis presents research theorising the use of social network sites (SNS) for the consumption of cultural goods. SNS are Internet-based applications that enable people to connect, interact, discover, and share user-generated content. They have transformed communication practices and are facilitating users to present their identity online through the disclosure of information on a profile. SNS are especially effective for propagating content far and wide within a network of connections. Cultural goods constitute hedonic experiential goods with cultural, artistic, and entertainment value, such as music, books, films, and fashion. Their consumption is culturally dependant and they have unique characteristics that distinguish them from utilitarian products. The way in which users express their identity on SNS is through the sharing of cultural interests and tastes. This makes cultural good consumption vulnerable to the exchange of content and ideas that occurs across an expansive network of connections within these social systems. This study proposes the lens of affordances to theorise the use of social network sites for the consumption of cultural goods. Qualitative case study research using two phases of data collection is proposed in the application of affordances to the research topic. The interaction between task, technology, and user characteristics is investigated by examining each characteristic in detail, before investigating the actual interaction between the user and the artifact for a particular purpose. The study contributes to knowledge by (i) improving our understanding of the affordances of social network sites for the consumption of cultural goods, (ii) demonstrating the role of task, technology and user characteristics in mediating user behaviour for user-artifact interactions, (iii) explaining the technical features and user activities important to the process of consuming cultural goods using social network sites, and (iv) theorising the consumption of cultural goods using SNS by presenting a theoretical research model which identifies empirical indicators of model constructs and maps out affordance dependencies and hierarchies. The study also provides a systematic research process for applying the concept of affordances to the study of system use.

Using electronic health record data for substance use Screening, Brief Intervention, and Referral to Treatment among adults with type 2 diabetes: Design of a National Drug Abuse Treatment Clinical Trials Network study.

BACKGROUND: The Affordable Care Act encourages healthcare systems to integrate behavioral and medical healthcare, as well as to employ electronic health records (EHRs) for health information exchange and quality improvement. Pragmatic research paradigms that employ EHRs in research are needed to produce clinical evidence in real-world medical settings for informing learning healthcare systems. Adults with comorbid diabetes and substance use disorders (SUDs) tend to use costly inpatient treatments; however, there is a lack of empirical data on implementing behavioral healthcare to reduce health risk in adults with high-risk diabetes. Given the complexity of high-risk patients' medical problems and the cost of conducting randomized trials, a feasibility project is warranted to guide practical study designs. METHODS: We describe the study design, which explores the feasibility of implementing substance use Screening, Brief Intervention, and Referral to Treatment (SBIRT) among adults with high-risk type 2 diabetes mellitus (T2DM) within a home-based primary care setting. Our study includes the development of an integrated EHR datamart to identify eligible patients and collect diabetes healthcare data, and the use of a geographic health information system to understand the social context in patients' communities. Analysis will examine recruitment, proportion of patients receiving brief intervention and/or referrals, substance use, SUD treatment use, diabetes outcomes, and retention. DISCUSSION: By capitalizing on an existing T2DM project that uses home-based primary care, our study results will provide timely clinical information to inform the designs and implementation of future SBIRT studies among adults with multiple medical conditions.

An investigation of assessment policy and practices in terms of broad social and educational purposes

Based upon relevant literature, this study investigated the assessment policy and practices for the BSc (Hons) Computing Science programme at the University of Greenwich (UOG), contextualising these in terms of broad social and educational purposes. It discusses Assessment, and then proceeds to give a critical evaluation of the assessment policy and practices at the UOG. Although this is one case study, because any of the features of the programme are generic to other programmes and institutions, it is of wider value and has further implications. The study was concluded in the summer of 2002. It concludes that overall, the programme's assessment policy and practices are well considered in terms of broad social and educational purposes, although it identifies and outlines several possible improvements, as well as raising some major issues still to be addressed which go beyond assessment practices.

"Practise what we preach": a social constructivist approach to blended learning

This presentation reports on the formal evaluation, through questionnaires, of a new Level 1 undergraduate course, for 130 student teachers, that uses blended learning. The course design seeks to radicalise the department’s approach to teaching, learning and assessment and use students as change agents. Its structure and content, model social constructivist approaches to learning. Building on the student’s experiences of and, reflections on, previous learning, promotes further learning through the support of “able others” (Vygotsky 1978), facilitating and nurturing a secure community of practice for students new to higher education. The course’s design incorporates individual, paired, small and large group activities and exploits online video, audio and text materials. Course units begin and end with face-to-face tutor-led activities. Online elements, including discussions and formative submissions, are tutor-mediated. Students work together face-to-face and online to read articles, write reflections, develop presentations, research and share experiences and resources. Summative joint assignments and peer assessments emphasise the value of collaboration and teamwork for academic, personal and professional development. Initial informal findings are positive, indicating that students have engaged readily with course content and structure, with few reporting difficulties accessing or using technology. Students have welcomed the opportunity to work together to tackle readings in a new genre, pilot presentation skills and receive and give constructive feedback to peers. Course tutors have indicated that depth and quality of study are evident, with regular online formative submissions enabling tutors to identify and engage directly with student’s needs, provide feedback and develop appropriately designed distance and face-to-face teaching materials. Pastoral tutors have indicated that students have reported non-engagement of peers, leading to the rapid application of academic or personal support. Outcomes of the formal evaluation will inform the development of Level 2 and 3 courses and influence the department’s use of blended learning.

Making the link: a customised social networking site can foster learning

Thanks to the internet, students today can do things that students of the past could not. They can learn formally or informally by interacting on social networking sites in a way that is not easily accomplished in a lecture theatre or classroom.

Mobile authoring of open educational resources for authentic learning scenarios

The proliferation of smartphones in the last decade and the number of publications in the field of authoring systems for computer-assisted learning depict a scenario that needs to be explored in order to facilitate the scaffolding of learning activities across contexts. Learning resources are traditionally designed in desktop-based authoring systems where the context is mostly restricted to the learning objective, capturing relevant case characteristics, or virtual situation models. Mobile authoring tools enable learners and teachers to foster universal access to educational resources not only providing channels to share, remix or re-contextualize these, but also capturing the context in-situ and in-time. As a further matter, authoring educational resources in a mobile context is an authentic experience where authors can link learning with their own daily life activities and reflections. The contribution of this manuscript is fourfold: first, the main barriers for ubiquitous and mobile authoring of educational resources are identified; second, recent research on mobile authoring tools is reviewed, and 10 key shortcomings of current approaches are identified; third, the design of a mobile environment to author educational resources (MAT for ARLearn) is presented, and the results of an evaluation of usability and hedonic quality are presented; fourth, conclusions and a research agenda for mobile authoring are discussed.