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].

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 Realization of Fuzzy ART

A neural network realization of the fuzzy Adaptive Resonance Theory (ART) algorithm is described. Fuzzy ART is capable of rapid stable learning of recognition categories in response to arbitrary sequences of analog or binary input patterns. Fuzzy ART incorporates computations from fuzzy set theory into the ART 1 neural network, which learns to categorize only binary input patterns, thus enabling the network to learn both analog and binary input patterns. In the neural network realization of fuzzy ART, signal transduction obeys a path capacity rule. Category choice is determined by a combination of bottom-up signals and learned category biases. Top-down signals impose upper bounds on feature node activations.

Working Memories for Storage and Recall of Arbitrary Temporal Sequences

A working memory model is described that is capable of storing and recalling arbitrary temporal sequences of events, including repeated items. These memories 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.

Comparative Performance Measures of Fuzzy ARTMAP, Learned Vector Quantization, and Back Propagation for Handwritten Character Recognition

This article compares the performance of Fuzzy ARTMAP with that of Learned Vector Quantization and Back Propagation on a handwritten character recognition task. Training with Fuzzy ARTMAP to a fixed criterion used many fewer epochs. Voting with Fuzzy ARTMAP yielded the highest recognition rates.

A What-and-Where Neural Network for Invariant Image Preprocessing

A feedforward neural network for invariant image preprocessing is proposed that represents the position1 orientation and size of an image figure (where it is) in a multiplexed spatial map. This map is used to generate an invariant representation of the figure that is insensitive to position1 orientation, and size for purposes of pattern recognition (what it is). A multiscale array of oriented filters followed by competition between orientations and scales is used to define the Where filter.

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.

Store Working Memory Networks for Storage and Recall of Arbitrary Temporal Sequences

Neural network models of working memory, called Sustained Temporal Order REcurrent (STORE) models, are described. They encode the invariant temporal order of sequential events in short term memory (STM) in a way that mimics cognitive data about working memory, including primacy, recency, and bowed order and error gradients. As new items are presented, the pattern of previously stored items is invariant in the sense that, relative activations remain constant through time. This invariant temporal order code enables 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 to design self-organizing temporal recognition and planning systems in which any subsequence of events may need to be categorized in order to to control and predict future behavior or external events. STORE models show how arbitrary event sequences may be invariantly stored, including repeated events. A preprocessor interacts with the working memory to represent event repeats in spatially separate locations. It is shown why at least two processing levels are needed to invariantly store events presented with variable durations and interstimulus intervals. It is also shown how network parameters control the type and shape of primacy, recency, or bowed temporal order gradients that will be stored.

History, revolution and the British popular novel: historical fiction in the romantic age

“History, Revolution and the British Popular Novel” takes as its focus the significant role which historical fiction played within the French Revolution debate and its aftermath. Examining the complex intersection of the genre with the political and historical dialogue generated by the French Revolution crisis, the thesis contends that contemporary fascination with the historical episode of the Revolution, and the fundamental importance of history to the disputes which raged about questions of tradition and change, and the meaning of the British national past, led to the emergence of increasingly complex forms of fictional historical narrative during the “war of ideas.” Considering the varying ways in which novelists such as Charlotte Smith, William Godwin, Mary Robinson, Helen Craik, Clara Reeve, John Moore, Edward Sayer, Mary Charlton, Ann Thomas, George Walker and Jane West engaged with the historical contexts of the Revolution debate, my discussion juxtaposes the manner in which English Jacobin novelists inserted the radical critique of the Jacobin novel into the wider arena of history with anti-Jacobin deployments of the historical to combat the revolutionary threat and internal moves for socio-political restructuring. I argue that the use of imaginative historical narrative to contribute to the ongoing dialogue surrounding the Revolution, and offer political and historical guidance to readers, represented a significant element within the literature of the Revolution crisis. The thesis also identifies the diverse body of historical fiction which materialised amidst the Revolution controversy as a key context within which to understand the emergence of Scott’s national historical novel in 1814, and the broader field of historical fiction in the era of Waterloo. Tracing the continued engagement with revolutionary and political concerns evident in the early Waverley novels, Frances Burney’s The Wanderer (1814), William Godwin’s Mandeville (1816), and Mary Shelley’s Valperga (1823), my discussion concludes by arguing that Godwin’s and Shelley’s extension of the mode of historical fiction initially envisioned by Godwin in the revolutionary decade, and their shared endeavour to retrieve the possibility enshrined within the republican past, appeared as a significant counter to the model of history and fiction developed by Walter Scott in the post-revolutionary epoch.

Digital signal processing and artificial intelligence for the automated classification of food allergy

As a by-product of the ‘information revolution’ which is currently unfolding, lifetimes of man (and indeed computer) hours are being allocated for the automated and intelligent interpretation of data. This is particularly true in medical and clinical settings, where research into machine-assisted diagnosis of physiological conditions gains momentum daily. Of the conditions which have been addressed, however, automated classification of allergy has not been investigated, even though the numbers of allergic persons are rising, and undiagnosed allergies are most likely to elicit fatal consequences. On the basis of the observations of allergists who conduct oral food challenges (OFCs), activity-based analyses of allergy tests were performed. Algorithms were investigated and validated by a pilot study which verified that accelerometer-based inquiry of human movements is particularly well-suited for objective appraisal of activity. However, when these analyses were applied to OFCs, accelerometer-based investigations were found to provide very poor separation between allergic and non-allergic persons, and it was concluded that the avenues explored in this thesis are inadequate for the classification of allergy. Heart rate variability (HRV) analysis is known to provide very significant diagnostic information for many conditions. Owing to this, electrocardiograms (ECGs) were recorded during OFCs for the purpose of assessing the effect that allergy induces on HRV features. It was found that with appropriate analysis, excellent separation between allergic and nonallergic subjects can be obtained. These results were, however, obtained with manual QRS annotations, and these are not a viable methodology for real-time diagnostic applications. Even so, this was the first work which has categorically correlated changes in HRV features to the onset of allergic events, and manual annotations yield undeniable affirmation of this. Fostered by the successful results which were obtained with manual classifications, automatic QRS detection algorithms were investigated to facilitate the fully automated classification of allergy. The results which were obtained by this process are very promising. Most importantly, the work that is presented in this thesis did not obtain any false positive classifications. This is a most desirable result for OFC classification, as it allows complete confidence to be attributed to classifications of allergy. Furthermore, these results could be particularly advantageous in clinical settings, as machine-based classification can detect the onset of allergy which can allow for early termination of OFCs. Consequently, machine-based monitoring of OFCs has in this work been shown to possess the capacity to significantly and safely advance the current state of clinical art of allergy diagnosis

Invertebrate diversity in Irish and British forests

Ireland and Britain were once covered in natural forest, but extensive anthropogenic deforestation reduced forest cover to less than 1% and 5 %, respectively, by the beginning of the 20th century. Large-scale afforestation has since increased the level of forest cover to 11% in Ireland and 12% in Britain, with the majority of planted forests comprising small monoculture plantations, many of which are of non - native conifer tree species. At present the forest cover of Ireland and Britain generally consists of small areas of remnant semi-natural woodland and pockets of these plantation forests within a predominantly agricultural landscape. Invertebrates comprise a large proportion of the biodiversity found within forested habitats. In particular, spiders and carabid beetles play an important role in food webs as both predators and prey and respond to small-scale changes in habitat structure, meaning they are particularly sensitive to forest management. Hoverflies play an important role in control and pollination and have been successfully used as indicators of habitat disturbance and quality. This research addressed a number of topics pertinent to the forest types present in the contemporary Irish and British landscapes and aimed to investigate the invertebrate diversity of these forests. Spiders and carabid beetles were sampled using pitfall trapping and hoverflies were sampled using Malaise net trapping. Topics included the impacts of afforestation, the importance of open space, the choice of tree species, and the use of indicators for biodiversity assessment, as well as rare native woodlands and the effect of grazing on invertebrate diversity. The results are discussed and evidence-based recommendations are made for forest policy and management to protect and enhance invertebrate biodiversity in order to promote sustainable forest management in Ireland and Britain.

Paradoxical worsening of tuberculosis in a heart-lung transplant recipient.

We report on a heart-lung transplant recipient who presented with pulmonary tuberculosis (TB) 2.5 months after transplantation and then developed a paradoxical reaction after 4 months of adequate anti-TB treatment. She eventually recovered with anti-TB and high-dose steroid treatments. METHODS: Using sequential bronchoalveolar lavages, we assessed the inflammatory response in the lung and investigated the alveolar immune response against a Mycobacterium tuberculosis antigen. RESULTS: The paradoxical reaction was characterized by a massive infiltration of the alveolar space by M. tuberculosis antigen-specific CD4(+) T cells and by the presence of a CD4(-)CD8(-) T lymphocyte subpopulation bearing phenotypic markers (CD16(+)/56(+)) classically associated with NK cells. CONCLUSION: This case report illustrates that even solid organ transplant recipients receiving intense triple-drug immune suppression may be able to develop a paradoxical reaction during TB treatment. Transplant physicians should be aware of this phenomenon in order to differentiate it from treatment failure.

Health events and the smoking cessation of middle aged Americans.

This study investigates the effect of serious health events including new diagnoses of heart attacks, strokes, cancers, chronic lung disease, chronic heart failure, diabetes, and heart disease on future smoking status up to 6 years postevent. Data come from the Health and Retirement Study, a nationally representative longitudinal survey of Americans aged 51-61 in 1991, followed every 2 years from 1992 to 1998. Smoking status is evaluated at each of three follow-ups, (1994, 1996, and 1998) as a function of health events between each of the four waves. Acute and chronic health events are associated with much lower likelihood of smoking both in the wave immediately following the event and up to 6 years later. However, future events do not retrospectively predict past cessation. In sum, serious health events have substantial impacts on cessation rates of older smokers. Notably, these effects persist for as much as 6 years after a health event.