Deformable Prototypes for Encoding Shape Categories in Image Databases

We describe a method for shape-based image database search that uses deformable prototypes to represent categories. Rather than directly comparing a candidate shape with all shape entries in the database, shapes are compared in terms of the types of nonrigid deformations (differences) that relate them to a small subset of representative prototypes. To solve the shape correspondence and alignment problem, we employ the technique of modal matching, an information-preserving shape decomposition for matching, describing, and comparing shapes despite sensor variations and nonrigid deformations. In modal matching, shape is decomposed into an ordered basis of orthogonal principal components. We demonstrate the utility of this approach for shape comparison in 2-D image databases.

Determining WWW User's Next Access and Its Application to Pre-fetching

World-Wide Web (WWW) services have grown to levels where significant delays are expected to happen. Techniques like pre-fetching are likely to help users to personalize their needs, reducing their waiting times. However, pre-fetching is only effective if the right documents are identified and if user's move is correctly predicted. Otherwise, pre-fetching will only waste bandwidth. Therefore, it is productive to determine whether a revisit will occur or not, before starting pre-fetching. In this paper we develop two user models that help determining user's next move. One model uses Random Walk approximation and the other is based on Digital Signal Processing techniques. We also give hints on how to use such models with a simple pre-fetching technique that we are developing.

Cortical Learning of Recognition Categories: A Resolution of the Exemplar Vs. Prototype Debate

Do humans and animals learn exemplars or prototypes when they categorize objects and events in the world? How are different degrees of abstraction realized through learning by neurons in inferotemporal and prefrontal cortex? How do top-down expectations influence the course of learning? Thirty related human cognitive experiments (the 5-4 category structure) have been used to test competing views in the prototype-exemplar debate. In these experiments, during the test phase, subjects unlearn in a characteristic way items that they had learned to categorize perfectly in the training phase. Many cognitive models do not describe how an individual learns or forgets such categories through time. Adaptive Resonance Theory (ART) neural models provide such a description, and also clarify both psychological and neurobiological data. Matching of bottom-up signals with learned top-down expectations plays a key role in ART model learning. Here, an ART model is used to learn incrementally in response to 5-4 category structure stimuli. Simulation results agree with experimental data, achieving perfect categorization in training and a good match to the pattern of errors exhibited by human subjects in the testing phase. These results show how the model learns both prototypes and certain exemplars in the training phase. ART prototypes are, however, unlike the ones posited in the traditional prototype-exemplar debate. Rather, they are critical patterns of features to which a subject learns to pay attention based on past predictive success and the order in which exemplars are experienced. Perturbations of old memories by newly arriving test items generate a performance curve that closely matches the performance pattern of human subjects. The model also clarifies exemplar-based accounts of data concerning amnesia.

Fuzzy ART

Adaptive Resonance Theory (ART) models are real-time neural networks for category learning, pattern recognition, and prediction. Unsupervised fuzzy ART and supervised fuzzy ARTMAP synthesize fuzzy logic and ART networks by exploiting the formal similarity between the computations of fuzzy subsethood and the dynamics of ART category choice, search, and learning. Fuzzy ART self-organizes stable recognition categories in response to arbitrary sequences of analog or binary input patterns. It generalizes the binary ART 1 model, replacing the set-theoretic: intersection (∩) with the fuzzy intersection (∧), or component-wise minimum. A normalization procedure called complement coding leads to a symmetric: theory in which the fuzzy inter:>ec:tion and the fuzzy union (∨), or component-wise maximum, play complementary roles. Complement coding preserves individual feature amplitudes while normalizing the input vector, and prevents a potential category proliferation problem. Adaptive weights :otart equal to one and can only decrease in time. A geometric interpretation of fuzzy AHT represents each category as a box that increases in size as weights decrease. A matching criterion controls search, determining how close an input and a learned representation must be for a category to accept the input as a new exemplar. A vigilance parameter (p) sets the matching criterion and determines how finely or coarsely an ART system will partition inputs. High vigilance creates fine categories, represented by small boxes. Learning stops when boxes cover the input space. With fast learning, fixed vigilance, and an arbitrary input set, learning stabilizes after just one presentation of each input. A fast-commit slow-recode option allows rapid learning of rare events yet buffers memories against recoding by noisy inputs. Fuzzy ARTMAP unites two fuzzy ART networks to solve supervised learning and prediction problems. A Minimax Learning Rule controls ARTMAP category structure, conjointly minimizing predictive error and maximizing code compression. Low vigilance maximizes compression but may therefore cause very different inputs to make the same prediction. When this coarse grouping strategy causes a predictive error, an internal match tracking control process increases vigilance just enough to correct the error. ARTMAP automatically constructs a minimal number of recognition categories, or "hidden units," to meet accuracy criteria. An ARTMAP voting strategy improves prediction by training the system several times using different orderings of the input set. Voting assigns confidence estimates to competing predictions given small, noisy, or incomplete training sets. ARPA benchmark simulations illustrate fuzzy ARTMAP dynamics. The chapter also compares fuzzy ARTMAP to Salzberg's Nested Generalized Exemplar (NGE) and to Simpson's Fuzzy Min-Max Classifier (FMMC); and concludes with a summary of ART and ARTMAP applications.

Fuzzy ART Choice Functions

Adaptive Resonance Theory (ART) models are real-time neural networks for category learning, pattern recognition, and prediction. Unsupervised fuzzy ART and supervised fuzzy ARTMAP networks synthesize fuzzy logic and ART by exploiting the formal similarity between tile computations of fuzzy subsethood and the dynamics of ART category choice, search, and learning. Fuzzy ART self-organizes stable recognition categories in response to arbitrary sequences of analog or binary input patterns. It generalizes the binary ART 1 model, replacing the set-theoretic intersection (∩) with the fuzzy intersection(∧), or component-wise minimum. A normalization procedure called complement coding leads to a symmetric theory in which the fuzzy intersection and the fuzzy union (∨), or component-wise maximum, play complementary roles. A geometric interpretation of fuzzy ART represents each category as a box that increases in size as weights decrease. This paper analyzes fuzzy ART models that employ various choice functions for category selection. One such function minimizes total weight change during learning. Benchmark simulations compare peformance of fuzzy ARTMAP systems that use different choice functions.

Towards a Unified Theory of Neocortex: Laminar Cortical Circuits for Vision and Cognition

A key goal of computational neuroscience is to link brain mechanisms to behavioral functions. The present article describes recent progress towards explaining how laminar neocortical circuits give rise to biological intelligence. These circuits embody two new and revolutionary computational paradigms: Complementary Computing and Laminar Computing. Circuit properties include a novel synthesis of feedforward and feedback processing, of digital and analog processing, and of pre-attentive and attentive processing. This synthesis clarifies the appeal of Bayesian approaches but has a far greater predictive range that naturally extends to self-organizing processes. Examples from vision and cognition are summarized. A LAMINART architecture unifies properties of visual development, learning, perceptual grouping, attention, and 3D vision. A key modeling theme is that the mechanisms which enable development and learning to occur in a stable way imply properties of adult behavior. It is noted how higher-order attentional constraints can influence multiple cortical regions, and how spatial and object attention work together to learn view-invariant object categories. In particular, a form-fitting spatial attentional shroud can allow an emerging view-invariant object category to remain active while multiple view categories are associated with it during sequences of saccadic eye movements. Finally, the chapter summarizes recent work on the LIST PARSE model of cognitive information processing by the laminar circuits of prefrontal cortex. LIST PARSE models the short-term storage of event sequences in working memory, their unitization through learning into sequence, or list, chunks, and their read-out in planned sequential performance that is under volitional control. LIST PARSE provides a laminar embodiment of Item and Order working memories, also called Competitive Queuing models, that have been supported by both psychophysical and neurobiological data. These examples show how variations of a common laminar cortical design can embody properties of visual and cognitive intelligence that seem, at least on the surface, to be mechanistically unrelated.

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.

Dutch influence in the urban landscape of Cork City pre-1800: Fact or myth?

The early years of the eighteenth century Irish port town, Cork saw an expansion of its city limits, an era of reconstruction both within and beyond the walls of its Medieval townscape and a reclamation of its marshlands to the east and west. New people, new ideas and the beginnings of new wealth infused the post Elizabethan character of the recently siege battered city. It also brought a desire for something different, something new, an opportunity to redefine the ambience and visual perception of the urban landscape and thereby make a statement about its intended cultural and social orientations. It brought an opportunity to re-imagine and model a new, continental style of place and surrounding environment.

Micronutrient intakes and the role of nutritional supplements in the diets of Irish adults and pre-school children

To investigate micronutrient intakes and the role of nutritional supplements in the diets of Irish adults aged 18-64 years and pre-school children aged 1-4 years. Analysis is based on data from the National Adult Nutrition Survey (NANS) (n=1274) and the National Pre-School Nutrition Survey (NPNS) (n=500). Food and beverage intakes and nutritional supplement use were recorded using 4-day food records. Nutrients were estimated using WISP© which is based on McCance and Widdowson’s The Composition of Foods, 6thEd and the Irish Food Composition Database. “Meats”, “milk/yoghurt”, “breads”, “fruit/fruit juices” and “breakfast cereals” made important contributions to the intakes of a number of micronutrients. Micronutrient intakes were generally adequate, with the exception of iron (in adult females and 1 year olds) and vitamin D (in all population groups). For iron, zinc, copper and vitamin B6, up to 2% of adults had intakes that exceeded the upper limit (UL). Small proportions of children had intakes of zinc (11%), copper (2%), retinol (4%) and folic acid (5%) exceeding the UL. Nutritional supplements (predominantly multivitamin and/or mineral preparations) were consumed by 28% of adults and 20% of pre-school children. Among users, supplements were effective in reducing the % with inadequate intakes for vitamins A and D (both population groups) and iron (adult females only). Supplement users had a lower prevalence of inadequate intakes for vitamin A and iron compared to non-users. In adults only, users had a lower prevalence of inadequate intakes for magnesium, calcium and zinc, and displayed better compliance with dietary recommendations and lifestyle characteristics compared with non-users. There is poor compliance among women of childbearing age for the recommendation to take a supplement containing 400µg/day of folic acid. These findings are important for the development of nutrition policies and future recommendations for adults and pre-school children in Ireland and the EU.

National food consumption surveys: micronutrient intakes and the role of fortified foods in the diets of Irish pre-school children and adults

This research investigated the micronutrient intakes of Irish pre-school children (1-4 years) and adults (18-64 years) and the role that fortified foods (FFs) play in the diets of these population groups. Dietary intake data were collected as part of the National Pre-school Nutrition Survey (NPNS) (2010-2011) and the National Adult Nutrition Survey (NANS) (2008-2010) using 4-day food and beverage records. Nutrient intakes were estimated using WISP©, which encompasses McCance and Widdowson’s The Composition of Foods and the Irish Food Composition Database. A FF is one in which one or more micronutrients are added. Key dietary sources of micronutrients in NPNS and NANS were “milk”, “meat & meat products”, “breakfast cereals”, “fruit & fruit juices” and “breads”. In general, intakes of most micronutrients were adequate with the exception of iron (1 year old children and adult women) and vitamin D (in all population groups). Small proportions of the pre-school population had intakes which exceeded the upper level (UL) (zinc: 11%, folic acid: 5%, retinol: 4%, copper: 2%). Less than 2% of adults had intakes of iron, copper, zinc and vitamin B6 which exceeded the UL. FFs were consumed by 97% of pre-school children and 82% of adults, representing 17% and 9% of mean daily energy intake respectively. Relative to energy intake, FFs contributed substantially greater proportions to intakes of key micronutrients, such as iron and vitamin D. FFs were effective in reducing the prevalence of inadequate micronutrient intakes in these population groups, particularly for iron in women and 1 year old children. FFs made a significant contribution to folate intake in women of childbearing age (72µg). FFs contributed greater proportions of carbohydrate and lower proportions of fat to the diets of consumers. Voluntary addition of nutrients to foods did not contribute appreciably to intakes exceeding the UL in these population groups.

A study of the extent to which Irish law, policy and practice allow for Ireland's application of the United Nations Convention on the Rights of the Child, 1989 to pre-natal children

The central research question of this thesis asks the extent to which Irish law, policy and practice allow for the application of the United Nations Convention on the Rights of the Child (CRC) to pre-natal children. First, it is demonstrated that pre-natal children can fall within the definition of ‘child’ under the Convention and so the possibility of applying the Convention to children before birth is opened. Many State Parties to the CRC have interpreted it as applicable to pre-natal children, while others have expressed that it only applies from birth. Ireland has not clarified whether or not it interprets it as being applicable from conception, birth, or some other point. The remainder of the thesis examines the extent to which Ireland interprets the CRC as applicable to the pre-natal child. First, the question of whether Ireland affords to the pre-natal child the right to life under Article 6(1) of the Convention is analysed. Given the importance of the indivisibility of rights under the Convention, the extent to which Ireland applies other CRC rights to pre-natal children is examined. The rights analysed are the right to protection from harm, the right to the provision of health care and the procedural right to representation. It is concluded that Ireland’s laws, policies and practices require urgent clarification on the issue of the extent to which rights such as protection, health care and representation apply to children before birth. In general, there are mixed and ad hoc approaches to these issues in Ireland and there exists a great deal of confusion amongst those working on the frontline with such children, such as health care professionals and social workers. The thesis calls for significant reform in this area in terms of law and policy, which will inform practice.

Transitions: From novice participation to expertise, pre-school 'matters' in an Irish pre-school community

This in depth, qualitative, participant observer study tracks children's transition experiences from novice to experienced membership of their pre-school community. It also considers adult roles in mediating this process in the context of the recent introduction of a universal free-pre-school year for children growing up in Ireland. Participation and the space to negotiate a participatory identity is understood in this study as a key element of positive experiences of early years transitions, within pre-school and beyond. The underlying theoretical framework is socio-cultural. This approach shifts from a scientific positivist view of thinking and learning as an individual inside the head process and asserts the historical, social, cultural as well as the situated context of learning and meaning making All participants, including myself as researcher, are recognised, explored and valued as embedded in the cultural context studied. In a sense, this approach tilts the worlds being observed through participation in them and reflects them in new light. The aim is to interpret and reflect the multiple realities constructed in this context rather than seek a truth out there waiting to be found. Special efforts are made to be invited in to and acknowledge children's expertise in the cultural worlds they negotiate with peers and adults in pre-school. The aim is to better understand what children may find motivating, interesting or problematic as they interpret reproduce and transform meaning within their play and learning worlds. My aim is for an honest rendering of the voices of stakeholders in pre-school communities from teachers, parents, and policy makers to children themselves. It makes visible constraints; potentials and possibilities within everyday Irish pre-school practices in the situated context studied as well as the broader societal, legislative and macro policy influences it reflects. Casting light on the taken for granted opens the possibility of adaptation or transformation. Transition itself can act as a tool to meet the changing needs of children on their developmental pathways across the life cycle

The ‘Celtic’ dimension of pre-first World War religious discourse in Britain: Wellesley Tudor Pole and the Glastonbury phenomenon

This article will explore the contribution made to the construction of discourse around religion outside of mainstream Christianity, at the turn of the twentieth century in Britain, by a Celticist movement as represented by Wellesley Tudor Pole (d.1968) and his connection to the Glastonbury phenomenon. I will detail the interconnectedness of individuals and movements occupying this discursive space and their interest in efforts to verify the authenticity of an artefact which Tudor Pole claimed was once in the possession of Jesus. Engagement with Tudor Pole’s quest to prove the provenance of the artefact, and his contention that a pre-Christian culture had existed in Ireland which had extended itself to Glastonbury and Iona creating the foundation for an authentic Western mystical tradition, is presented as one facet of a broader, contemporary discourse on alternative ideas and philosophies. In conclusion, I will juxtapose Tudor Pole’s fascination with Celtic origins and the approach of leading figures in the ‘Celtic Revival’ in Ireland, suggesting intersections and alterity in the construction of their worldview. The paper forms part of a chapter in a thesis under-preparation which examines the construction of discourse on religion outside of mainstream Christianity at the turn of the twentieth century, and in particular the role played by visiting religious reformers from Asia. The aim is to recover the (mostly forgotten) history of these engagements.

Un "Notre-Père" en copte à Médinet Abou

Identification et réédition d'une inscription copte fragmentaire portant le texte du Notre-Père. L'inscription était peinte à l'intérieur d'une maison adossée à un mur du temple de Ramsès III à Médinet Abou, devenu le village de Djèmé à l'époque chrétienne.