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.

Texture Segregation By Visual Cortex: Perceptual Grouping, Attention, and Learning

A neural model is proposed of how laminar interactions in the visual cortex may learn and recognize object texture and form boundaries. The model brings together five interacting processes: region-based texture classification, contour-based boundary grouping, surface filling-in, spatial attention, and object attention. The model shows how form boundaries can determine regions in which surface filling-in occurs; how surface filling-in interacts with spatial attention to generate a form-fitting distribution of spatial attention, or attentional shroud; how the strongest shroud can inhibit weaker shrouds; and how the winning shroud regulates learning of texture categories, and thus the allocation of object attention. The model can discriminate abutted textures with blurred boundaries and is sensitive to texture boundary attributes like discontinuities in orientation and texture flow curvature as well as to relative orientations of texture elements. The model quantitatively fits a large set of human psychophysical data on orientation-based textures. Object boundar output of the model is compared to computer vision algorithms using a set of human segmented photographic images. The model classifies textures and suppresses noise using a multiple scale oriented filterbank and a distributed Adaptive Resonance Theory (dART) classifier. The matched signal between the bottom-up texture inputs and top-down learned texture categories is utilized by oriented competitive and cooperative grouping processes to generate texture boundaries that control surface filling-in and spatial attention. Topdown modulatory attentional feedback from boundary and surface representations to early filtering stages results in enhanced texture boundaries and more efficient learning of texture within attended surface regions. Surface-based attention also provides a self-supervising training signal for learning new textures. Importance of the surface-based attentional feedback in texture learning and classification is tested using a set of textured images from the Brodatz micro-texture album. Benchmark studies vary from 95.1% to 98.6% with attention, and from 90.6% to 93.2% without attention.

Language legislation in Ireland and the United Kingdom: Exploring the gaps between theory and practice

The central objective in this thesis is to explore the gaps between the normative justifications advanced for language rights and language legislative protection and the effective realisation of those rights and legislative provisions in practice. This objective is achieved by examining the scope and application of language rights and legislative provisions within language legislation in Ireland and the United Kingdom. Drawing on Canadian jurisprudence advocating for language rights to be recognised as “purposeful”, the thesis considers the extent to which Ireland and the United Kingdom have limited the acceptance of positive obligations as they relate to the provision of language services in the public sphere. In arguing that language rights are distinct in nature, the thesis suggests that in order for language rights to be effectively realised, an approach to language rights and language legislation more generally must be underpinned by a substantive vision of equality, otherwise language rights and legislative provisions merely amount to symbolic recognition and vacuous rhetoric as opposed to being substantive and enabling rights and provisions. Having said that, the thesis also recognises and elucidates the practical difficulties that arise in the realisation of language rights and language legislative provisions and in doing so seeks to stimulate further dialogue about the nature and limits of language rights and language legislation.

Within the carnal: re-reading Merleau-Ponty through the language of drawing

In order to present visual art as a paradigm for philosophy, Merleau-Ponty investigated the creative processes of artists whose work corresponded closely with his philosophical ideas. His essays on art are widely valued for emphasising process over product, and for challenging the primacy of the written word in all spheres of human expression. While it is clear that he initially favoured painting, Merleau-Ponty began to develop a much deeper understanding of the complexities of how art is made in his late work in parallel with his advancement of a new ontology. Although his ontology remains unfinished and only exists as working notes and a manuscript entitled The Visible and Invisible, Merleau-Ponty had begun to appreciate the fundamental role drawing plays in the making of art and the creation of a language of expression that is as vital as the written or spoken word. Through an examination of Merleau-Ponty’s unfinished manuscript and working notes my thesis will investigate his working methods and use of materials and also explore how he processed his ideas by using my own art practice as the basis of my research. This research will take the form of an inquiry into how the unfinished and incomplete nature of text and artworks, while they are still ‘works in progress’, can often reveal the more human and carnal components of creative processes. Applying my experience as a practitioner and a teacher in an art school, I focus on the significance of drawing practice for Merleau-Ponty’s later work, in order to rebalance an overemphasis on painting in the literature. Understanding the differences between these two art forms, and how they are taught, can offer an alternative engagement with Merleau-Ponty’s later work and his struggle to find a language to express his developing new ontology. In addition, by re-reading his work through the language of drawing, I believe we gain new insights which reaffirm Merleau-Ponty's relevance to contemporary art making and aesthetics.

Neural mechanisms of context effects on face recognition: automatic binding and context shift decrements.

Although people do not normally try to remember associations between faces and physical contexts, these associations are established automatically, as indicated by the difficulty of recognizing familiar faces in different contexts ("butcher-on-the-bus" phenomenon). The present fMRI study investigated the automatic binding of faces and scenes. In the face-face (F-F) condition, faces were presented alone during both encoding and retrieval, whereas in the face/scene-face (FS-F) condition, they were presented overlaid on scenes during encoding but alone during retrieval (context change). Although participants were instructed to focus only on the faces during both encoding and retrieval, recognition performance was worse in the FS-F than in the F-F condition ("context shift decrement" [CSD]), confirming automatic face-scene binding during encoding. This binding was mediated by the hippocampus as indicated by greater subsequent memory effects (remembered > forgotten) in this region for the FS-F than the F-F condition. Scene memory was mediated by right parahippocampal cortex, which was reactivated during successful retrieval when the faces were associated with a scene during encoding (FS-F condition). Analyses using the CSD as a regressor yielded a clear hemispheric asymmetry in medial temporal lobe activity during encoding: Left hippocampal and parahippocampal activity was associated with a smaller CSD, indicating more flexible memory representations immune to context changes, whereas right hippocampal/rhinal activity was associated with a larger CSD, indicating less flexible representations sensitive to context change. Taken together, the results clarify the neural mechanisms of context effects on face recognition.

Facial and expression recognition for the blind using computer vision

Gemstone Team FACE

I can see it both ways: first- and third-person visual perspectives at retrieval.

The number of studies examining visual perspective during retrieval has recently grown. However, the way in which perspective has been conceptualized differs across studies. Some studies have suggested perspective is experienced as either a first-person or a third-person perspective, whereas others have suggested both perspectives can be experienced during a single retrieval attempt. This aspect of perspective was examined across three studies, which used different measurement techniques commonly used in studies of perspective. Results suggest that individuals can experience more than one perspective when recalling events. Furthermore, the experience of the two perspectives correlated differentially with ratings of vividness, suggesting that the two perspectives should not be considered in opposition of one another. We also found evidence of a gender effect in the experience of perspective, with females experiencing third-person perspectives more often than males. Future studies should allow for the experience of more than one perspective during retrieval.

Mapping the structure of perceptual and visual-motor abilities in healthy young adults.

The ability to quickly detect and respond to visual stimuli in the environment is critical to many human activities. While such perceptual and visual-motor skills are important in a myriad of contexts, considerable variability exists between individuals in these abilities. To better understand the sources of this variability, we assessed perceptual and visual-motor skills in a large sample of 230 healthy individuals via the Nike SPARQ Sensory Station, and compared variability in their behavioral performance to demographic, state, sleep and consumption characteristics. Dimension reduction and regression analyses indicated three underlying factors: Visual-Motor Control, Visual Sensitivity, and Eye Quickness, which accounted for roughly half of the overall population variance in performance on this battery. Inter-individual variability in Visual-Motor Control was correlated with gender and circadian patters such that performance on this factor was better for males and for those who had been awake for a longer period of time before assessment. The current findings indicate that abilities involving coordinated hand movements in response to stimuli are subject to greater individual variability, while visual sensitivity and occulomotor control are largely stable across individuals.

Japanese language teaching: a communicative approach

Japanese Language Teaching examines the practical aspects of the acquisition of Japanese as a second language, underpinned by current theory and research. Each chapter examines the theory and practice of language teaching, and progresses to a consideration of the practical design of tasks for teaching. The final section applies theory and practice to an empirical case study, drawn from a classroom with Japanese as a second language. With its emphasis on practice underpinned by contemporary theory, this book will be of interest to postgraduates studying second language acquisition and applied linguistics. [Source: publisher's description].

Towards Cloud-Based Knowledge Capturing Based on Natural Language Processing

Paper presented at the Cloud Forward Conference 2015, October 6th-8th, Pisa

Efficient FPGA Hardware Development: A Multi-Language Approach

This paper presents a multi-language framework to FPGA hardware development which aims to satisfy the dual requirement of high-level hardware design and efficient hardware implementation. The central idea of this framework is the integration of different hardware languages in a way that harnesses the best features of each language. This is illustrated in this paper by the integration of two hardware languages in the form of HIDE: a structured hardware language which provides more abstract and elegant hardware descriptions and compositions than are possible in traditional hardware description languages such as VHDL or Verilog, and Handel-C: an ANSI C-like hardware language which allows software and hardware engineers alike to target FPGAs from high-level algorithmic descriptions. On the one hand, HIDE has proven to be very successful in the description and generation of highly optimised parameterisable FPGA circuits from geometric descriptions. On the other hand, Handel-C has also proven to be very successful in the rapid design and prototyping of FPGA circuits from algorithmic application descriptions. The proposed integrated framework hence harnesses HIDE for the generation of highly optimised circuits for regular parts of algorithms, while Handel-C is used as a top-level design language from which HIDE functionality is dynamically invoked. The overall message of this paper posits that there need not be an exclusive choice between different hardware design flows. Rather, an integrated framework where different design flows can seamlessly interoperate should be adopted. Although the idea might seem simple prima facie, it could have serious implications on the design of future generations of hardware languages.

Speech Recognition with unknown partial feature corruption - a review of the union model

This paper provides a summary of our studies on robust speech recognition based on a new statistical approach – the probabilistic union model. We consider speech recognition given that part of the acoustic features may be corrupted by noise. The union model is a method for basing the recognition on the clean part of the features, thereby reducing the effect of the noise on recognition. To this end, the union model is similar to the missing feature method. However, the two methods achieve this end through different routes. The missing feature method usually requires the identity of the noisy data for noise removal, while the union model combines the local features based on the union of random events, to reduce the dependence of the model on information about the noise. We previously investigated the applications of the union model to speech recognition involving unknown partial corruption in frequency band, in time duration, and in feature streams. Additionally, a combination of the union model with conventional noise-reduction techniques was studied, as a means of dealing with a mixture of known or trainable noise and unknown unexpected noise. In this paper, a unified review, in the context of dealing with unknown partial feature corruption, is provided into each of these applications, giving the appropriate theory and implementation algorithms, along with an experimental evaluation.

Goal Recognition through Goal Graph Analysis

We present a novel approach to goal recognition based on a two-stage paradigm of graph construction and analysis. First, a graph structure called a Goal Graph is constructed to represent the observed actions, the state of the world, and the achieved goals as well as various connections between these nodes at consecutive time steps. Then, the Goal Graph is analysed at each time step to recognise those partially or fully achieved goals that are consistent with the actions observed so far. The Goal Graph analysis also reveals valid plans for the recognised goals or part of these goals. Our approach to goal recognition does not need a plan library. It does not suffer from the problems in the acquisition and hand-coding of large plan libraries, neither does it have the problems in searching the plan space of exponential size. We describe two algorithms for Goal Graph construction and analysis in this paradigm. These algorithms are both provably sound, polynomial-time, and polynomial-space. The number of goals recognised by our algorithms is usually very small after a sequence of observed actions has been processed. Thus the sequence of observed actions is well explained by the recognised goals with little ambiguity. We have evaluated these algorithms in the UNIX domain, in which excellent performance has been achieved in terms of accuracy, efficiency, and scalability.

Organs of the human brain, created by the human hand? The social epistemology of information technology

Purpose
– Information science has been conceptualized as a partly unreflexive response to developments in information and computer technology, and, most powerfully, as part of the gestalt of the computer. The computer was viewed as an historical accident in the original formulation of the gestalt. An alternative, and timely, approach to understanding, and then dissolving, the gestalt would be to address the motivating technology directly, fully recognizing it as a radical human construction. This paper aims to address the issues.

Design/methodology/approach
– The paper adopts a social epistemological perspective and is concerned with collective, rather than primarily individual, ways of knowing.

Findings
– Information technology tends to be received as objectively given, autonomously developing, and causing but not itself caused, by the language of discussions in information science. It has also been characterized as artificial, in the sense of unnatural, and sometimes as threatening. Attitudes to technology are implied, rather than explicit, and can appear weak when articulated, corresponding to collective repression.

Research limitations/implications
– Receiving technology as objectively given has an analogy with the Platonist view of mathematical propositions as discovered, in its exclusion of human activity, opening up the possibility of a comparable critique which insists on human agency.

Originality/value
– Apprehensions of information technology have been raised to consciousness, exposing their limitations.