ART-EMAP: A Neural Network Architecture for Object Recognition by Evidence Accumulation

A new neural network architecture is introduced for the recognition of pattern classes after supervised and unsupervised learning. Applications include spatio-temporal image understanding and prediction and 3-D object recognition from a series of ambiguous 2-D views. The architecture, called ART-EMAP, achieves a synthesis of adaptive resonance theory (ART) and spatial and temporal evidence integration for dynamic predictive mapping (EMAP). ART-EMAP extends the capabilities of fuzzy ARTMAP in four incremental stages. Stage 1 introduces distributed pattern representation at a view category field. Stage 2 adds a decision criterion to the mapping between view and object categories, delaying identification of ambiguous objects when faced with a low confidence prediction. Stage 3 augments the system with a field where evidence accumulates in medium-term memory (MTM). Stage 4 adds an unsupervised learning process to fine-tune performance after the limited initial period of supervised network training. Each ART-EMAP stage is illustrated with a benchmark simulation example, using both noisy and noise-free data. A concluding set of simulations demonstrate ART-EMAP performance on a difficult 3-D object recognition problem.

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.

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.

Symmetrical freedom quilts: the ethnomathematics of ways of communication, liberation, and art

Symmetrical Freedom Quilts may be considered as links between mathematics, history, ethnomathematics, and the art of quilting. A quilt theme is a pedagogical way to integrate mathematics, art, and history in an interdisciplinary approach. This article combines an ethnomathematical-historical perspective by elaborating a history project related to the Underground Railroad. This work will allow teachers to develop classroom projects that help students to better understand geometry, especially concepts of symmetry and transformations. One of the objectives of this project is to stimulate student’s creativity and interest, because quilts may be considered as cultural and mathematical expressions of student’s daily life.

Transdisciplinary Science: A Path to Understanding the Interactions Among Ocean Acidification, Ecosystems, and Society

The global nature of ocean acidification (OA) transcends habitats, ecosystems, regions, and science disciplines. The scientific community recognizes that the biggest challenge in improving understanding of how changing OA conditions affect ecosystems, and associated consequences for human society, requires integration of experimental, observational, and modeling approaches from many disciplines over a wide range of temporal and spatial scales. Such transdisciplinary science is the next step in providing relevant, meaningful results and optimal guidance to policymakers and coastal managers. We discuss the challenges associated with integrating ocean acidification science across funding agencies, institutions, disciplines, topical areas, and regions, and the value of unifying science objectives and activities to deliver insights into local, regional, and global scale impacts. We identify guiding principles and strategies for developing transdisciplinary research in the ocean acidification science community.

Art, adolescence and Social Work: Anja, the invisible manager

This article has been written with the intention of being able to analyse the contributions of art —theatre, in this case— to the practice of social work. For this purpose, we have chosen to read the social reality in which we intervene through the lens of social constructionism. This helps us to rescue the social and subjective side of art, and, moreover, to recover the depathologization of the subject in professional intervention. Thus, using a practical case taken from work with adolescents in the German FSJ programme, hand-in-hand with a young girl called Anja we trace the developmental and sociological aspects of adolescence in order to later address certain common points of art and psychosocial work. Art will hence be redefined as a transitional object allowing questions to be addressed relating to (self-) perception, attachment, communication and changes in conduct as the ultimate goal of professional action. Lastly, we note the limitations and risks of art-based intervention, in order to conclude with a final synopsis.

Art as an educative and social tool

Since remote times, certain sectors of society have been exposed to inequality and vulnerability, where adequate intervention processes have become conspicuous because of their absence. Nowadays, current societies have the responsibility of contributing, based on their experience and knowledge, with more efficient policies and programs that improve the life quality of the most disadvantaged. It is here where art and its different tools play a very important role, not only on a physical level, but also as an education tool that allows the development of emotional, mental and communicative skills. The aim of this paper is to make clear the potential of art as an instrument of social and educational intervention. It starts by showing worldwide-collected experience related to education and arts, and then, it acquaints the reader with two parallel intervention projects that worked with youths under social vulnerability conditions. These interventions were developed based on a qualitative research (Grounded theory), using as methodology “The Artistic Mediation” with emphasis on body language. This methodology helped researchers to get close to the participants and to know their experiences and emotions. At the same time, it was possible to evidence the positive effects of educative interventions through art. These workshops were based on an artistic methodology especially focused on body language. Data in this work is qualitative, and as such, it permits a special approach to the personal and emotional experiences of the participants; clearly showing the positive effects of the referenced practice on them.

Metaphor and Maltese Art: Explorations in the Temple Period

Temple Period Malta in the 3rd millennium BC saw the production of a range of figurative and decorative art and architecture that implies a richly populated spiritual and cognitive world associated with ritual practice in life and death. The paper explores the potential to categorize the figurative art into distinct groups, and how these various images might represent aspects of the cosmology and social concerns of a prehistoric island society.

Impure Thinking Practices and Clinical Acts: The Sonorous Becomings of Heidi Fast

This article introduces the recent sound works of Heidi Fast, a Finnish voice and performance artist. Fast’s creative practice operates between art and philosophy, and articulates several ‘zones of becoming’: what Fast designates as ‘the clinical’, ‘the virtual’ and ‘vocal thought-material’. Using a methodology of routing, the article shows how these zones emerge as aesthetic, ethical and political concerns within Fast’s work. Since 2005, Fast’s sound works have variously taken shape as miniature concerts, social sculptures, imaginary soundscapes and environmental music performances. Drawing upon the writings of theorists who have helped shape her practice, this article argues that Fast uses sound and voice to propose an ‘actualising philosophy’. This philosophy actualises virtualities (unrealised potentials), affecting transformative shifts through tiny mutations in perceptions and behaviours.

Anthropology, Socialist Prediction and William Morris’s Commonweal

In the late nineteenth century, a number of writers turned to anthropology to predict a socialist future. They included prominent revolutionary socialists: Friedrich Engels, William Morris and members of the Socialist League. Contextualising the appropriation of the anthropologist Lewis Henry Morgan by such readers, this article also pays particular attention to socialist popularisations of anthropology, particularly those by Morris and his fellow writers in his penny weekly, the Commonweal. Focusing on Morris’s articles on ancient society helps to illuminate his own understanding of history, art and socialism. It also sheds new light on his predictive fiction News from Nowhere, which was originally read alongside Commonweal non-fiction. Both, I will argue, encouraged readers to see the future in the struggles of the ancient past.

Conflict, Transformation, and Former Loyalist Paramilitary Prisoners in Northern Ireland

Following the 1998 Belfast Agreement in Northern Ireland, levels of paramilitary violence have declined substantially. Among loyalists, the Ulster Volunteer Force (UVF) and associated Red Hand Commando (RHC) have formally renounced violence, and dissolved their 'military structures', and perhaps the most reticent of all of the major paramilitary groupings, the Ulster Defence Association (UDA), has taken on board the central tenets of conflict transformation, and 'stood down' all of its 'active service units' in the Ulster Freedom Fighters (UFF). Thus, paramilitary violence now is mainly confined to the activities of 'dissident' republican groups, notably the Real and Continuity IRAs, although low-level sectarian violence remains a problem. Such dramatic societal and political change has resulted in a focus on the roles of formal party political leadership as agents of social change. This gaze, however, tends to obscure other important events such as the efforts, structures and approaches taken at the grassroots level to uphold and sustain conflict transformation and to maintain a reduction in violence. This article provides analysis of the role played by former loyalist paramilitary combatants in conflict transformation, and draws on material obtained through significant access to those former paramilitaries engaged in processes of societal shifts. In both personal and structural terms there is evidence of former combatants working to diminish the political tensions that remain as a result of the long-term inter-communal hostility developed across decades of violence and conflict.

The Critical Reading of the Images Associated with Science-Related News Reports: Establishing a knowledge, skills, and attitudes framework

For the majority of adults, the media constitute their main source of information about science and science-related matters impacting on society. To help prepare young people to engage with science in the media, teachers are being exhorted to equip their students with the knowledge, skills, and attitudes to respond critically to science-related news reports. Typically, such reports comprise not only text, but also visual elements. These images are not simply adjuncts to the written word; they are integral to meaning-making. Though science teachers make considerable use of newspaper images, they tend to view these representations unproblematically, underestimating their potential ambiguity, complexity, and role in framing media messages. They rarely aim to develop students’ ability to ‘read’, critically, such graphics. Moreover, research into how this might be achieved is limited and, consequently, research-informed guidance which could support this instruction is lacking. This paper describes a study designed to formulate a framework for such teaching. Science communication scholars, science journalists and media educators with acknowledged relevant expertise were surveyed to ascertain what knowledge, skills, and attitudes they deemed useful to engagement with science related news images. Their proposals were recast as learning intentions (instructional objectives), and science and English teachers collaborated to suggest which could be addressed with secondary school students and the age group best suited to their introduction. The outcome is an inventory of learning intentions on which teachers could draw to support their planning of instructional sequences aimed at developing students’ criticality in respect of the totality of science news reports.

Catholics, Science and Civic Culture in Victorian Belfast

The connections between science and civic culture in the Victorian period have been extensively, and intensively, investigated over the past several decades. Limited attention, however, has been paid to Irish urban contexts. Roman Catholic attitudes towards science in the nineteenth century have also been neglected beyond a rather restricted set of thinkers and topics. This paper is offered as a contribution to addressing these lacunae, and examines in detail the complexities involved in Catholic engagement with science in Victorian Belfast. The political and civic geographies of Catholic involvement in scientific discussions in a divided town are uncovered through an examination of five episodes in the unfolding history of Belfast's intellectual culture. The paper stresses the importance of attending to the particularities of local politics and scientific debate for understanding the complex realities of Catholic appropriations of science in a period and urban context profoundly shaped by competing political and religious factions. It also reflects more generally on how the Belfast story supplements and challenges scholarship on the historical relations between Catholicism and science.