Global exponential periodicity of a class of bidirectional associative memory networks with finite distributed delays

In this paper, we study the periodic oscillatory behavior of a class of bidirectional associative memory (BAM) networks with finite distributed delays. A set of criteria are proposed for determining global exponential periodicity of the proposed BAM networks, which assume neither differentiability nor monotonicity of the activation function of each neuron. In addition, our criteria are easily checkable. (c) 2005 Elsevier Inc. All rights reserved.

Design of associative memories using cellular neural networks

Cellular neural networks (CNNs) have locally connected neurons. This characteristic makes CNNs adequate for hardware implementation and, consequently, for their employment on a variety of applications as real-time image processing and construction of efficient associative memories. Adjustments of CNN parameters is a complex problem involved in the configuration of CNN for associative memories. This paper reviews methods of associative memory design based on CNNs, and provides comparative performance analysis of these approaches.

Contribution of neural networks to Alzheimer disease's progression.

The neuropathology of Alzheimer disease is characterized by senile plaques, neurofibrillary tangles and cell death. These hallmarks develop according to the differential vulnerability of brain networks, senile plaques accumulating preferentially in the associative cortical areas and neurofibrillary tangles in the entorhinal cortex and the hippocampus. We suggest that the main aetiological hypotheses such as the beta-amyloid cascade hypothesis or its variant, the synaptic beta-amyloid hypothesis, will have to consider neural networks not just as targets of degenerative processes but also as contributors of the disease's progression and of its phenotype. Three domains of research are highlighted in this review. First, the cerebral reserve and the redundancy of the network's elements are related to brain vulnerability. Indeed, an enriched environment appears to increase the cerebral reserve as well as the threshold of disease's onset. Second, disease's progression and memory performance cannot be explained by synaptic or neuronal loss only, but also by the presence of compensatory mechanisms, such as synaptic scaling, at the microcircuit level. Third, some phenotypes of Alzheimer disease, such as hallucinations, appear to be related to progressive dysfunction of neural networks as a result, for instance, of a decreased signal to noise ratio, involving a diminished activity of the cholinergic system. Overall, converging results from studies of biological as well as artificial neural networks lead to the conclusion that changes in neural networks contribute strongly to Alzheimer disease's progression.

Self-organising neural networks for adaptive control

Self-organizing neural networks have been implemented in a wide range of application areas such as speech processing, image processing, optimization and robotics. Recent variations to the basic model proposed by the authors enable it to order state space using a subset of the input vector and to apply a local adaptation procedure that does not rely on a predefined test duration limit. Both these variations have been incorporated into a new feature map architecture that forms an integral part of an Hybrid Learning System (HLS) based on a genetic-based classifier system. Problems are represented within HLS as objects characterized by environmental features. Objects controlled by the system have preset targets set against a subset of their features. The system's objective is to achieve these targets by evolving a behavioural repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS — long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This paper presents a description of the HLS architecture and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behaviour of the system on a simple control task.

Optimising memory usage in n-tuple neural networks

The use of n-tuple or weightless neural networks as pattern recognition devices is well known (Aleksander and Stonham, 1979). They have some significant advantages over the more common and biologically plausible networks, such as multi-layer perceptrons; for example, n-tuple networks have been used for a variety of tasks, the most popular being real-time pattern recognition, and they can be implemented easily in hardware as they use standard random access memories. In operation, a series of images of an object are shown to the network, each being processed suitably and effectively stored in a memory called a discriminator. Then, when another image is shown to the system, it is processed in a similar manner and the system reports whether it recognises the image; is the image sufficiently similar to one already taught? If the system is to be able to recognise and discriminate between m-objects, then it must contain m-discriminators. This can require a great deal of memory. This paper describes various ways in which memory requirements can be reduced, including a novel method for multiple discriminator n-tuple networks used for pattern recognition. By using this method, the memory normally required to handle m-objects can be used to recognise and discriminate between 2^m — 2 objects.

Auto-associative memory using n-tuple techniques

The use of n-tuple or weightless neural networks as pattern recognition devices has been well documented. They have a significant advantages over more common networks paradigms, such as the multilayer perceptron in that they can be easily implemented in digital hardware using standard random access memories. To date, n-tuple networks have predominantly been used as fast pattern classification devices. The paper describes how n-tuple techniques can be used in the hardware implementation of a general auto-associative network.

Recognition of noisy images by PLL networks

We use networks composed of three phase-locked loops (PLLs), where one of them is the master, for recognizing noisy images. The values of the coupling weights among the PLLs control the noise level which does not affect the successful identification of the input image. Analytical results and numerical tests are presented concerning the scheme performance. (c) 2008 Elsevier B.V. All rights reserved.

On Recurrent and Deep Neural Networks

L'apprentissage profond est un domaine de recherche en forte croissance en apprentissage automatique qui est parvenu à des résultats impressionnants dans différentes tâches allant de la classification d'images à la parole, en passant par la modélisation du langage. Les réseaux de neurones récurrents, une sous-classe d'architecture profonde, s'avèrent particulièrement prometteurs. Les réseaux récurrents peuvent capter la structure temporelle dans les données. Ils ont potentiellement la capacité d'apprendre des corrélations entre des événements éloignés dans le temps et d'emmagasiner indéfiniment des informations dans leur mémoire interne. Dans ce travail, nous tentons d'abord de comprendre pourquoi la profondeur est utile. Similairement à d'autres travaux de la littérature, nos résultats démontrent que les modèles profonds peuvent être plus efficaces pour représenter certaines familles de fonctions comparativement aux modèles peu profonds. Contrairement à ces travaux, nous effectuons notre analyse théorique sur des réseaux profonds acycliques munis de fonctions d'activation linéaires par parties, puisque ce type de modèle est actuellement l'état de l'art dans différentes tâches de classification. La deuxième partie de cette thèse porte sur le processus d'apprentissage. Nous analysons quelques techniques d'optimisation proposées récemment, telles l'optimisation Hessian free, la descente de gradient naturel et la descente des sous-espaces de Krylov. Nous proposons le cadre théorique des méthodes à région de confiance généralisées et nous montrons que plusieurs de ces algorithmes développés récemment peuvent être vus dans cette perspective. Nous argumentons que certains membres de cette famille d'approches peuvent être mieux adaptés que d'autres à l'optimisation non convexe. La dernière partie de ce document se concentre sur les réseaux de neurones récurrents. Nous étudions d'abord le concept de mémoire et tentons de répondre aux questions suivantes: Les réseaux récurrents peuvent-ils démontrer une mémoire sans limite? Ce comportement peut-il être appris? Nous montrons que cela est possible si des indices sont fournis durant l'apprentissage. Ensuite, nous explorons deux problèmes spécifiques à l'entraînement des réseaux récurrents, à savoir la dissipation et l'explosion du gradient. Notre analyse se termine par une solution au problème d'explosion du gradient qui implique de borner la norme du gradient. Nous proposons également un terme de régularisation conçu spécifiquement pour réduire le problème de dissipation du gradient. Sur un ensemble de données synthétique, nous montrons empiriquement que ces mécanismes peuvent permettre aux réseaux récurrents d'apprendre de façon autonome à mémoriser des informations pour une période de temps indéfinie. Finalement, nous explorons la notion de profondeur dans les réseaux de neurones récurrents. Comparativement aux réseaux acycliques, la définition de profondeur dans les réseaux récurrents est souvent ambiguë. Nous proposons différentes façons d'ajouter de la profondeur dans les réseaux récurrents et nous évaluons empiriquement ces propositions.

Neural networks for identification of nonlinear systems under random piecewise polynomial disturbances

The problem of identification of a nonlinear dynamic system is considered. A two-layer neural network is used for the solution of the problem. Systems disturbed with unmeasurable noise are considered, although it is known that the disturbance is a random piecewise polynomial process. Absorption polynomials and nonquadratic loss functions are used to reduce the effect of this disturbance on the estimates of the optimal memory of the neural-network model.

Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

THE RESONATE-AND-FIRE NEURON: TIME DEPENDENT AND FREQUENCY SELECTIVE NEURONS IN NEURAL NETWORKS

The means through which the nervous system perceives its environment is one of the most fascinating questions in contemporary science. Our endeavors to comprehend the principles of neural science provide an instance of how biological processes may inspire novel methods in mathematical modeling and engineering. The application ofmathematical models towards understanding neural signals and systems represents a vibrant field of research that has spanned over half a century. During this period, multiple approaches to neuronal modeling have been adopted, and each approach is adept at elucidating a specific aspect of nervous system function. Thus while bio-physical models have strived to comprehend the dynamics of actual physical processes occurring within a nerve cell, the phenomenological approach has conceived models that relate the ionic properties of nerve cells to transitions in neural activity. Further-more, the field of neural networks has endeavored to explore how distributed parallel processing systems may become capable of storing memory. Through this project, we strive to explore how some of the insights gained from biophysical neuronal modeling may be incorporated within the field of neural net-works. We specifically study the capabilities of a simple neural model, the Resonate-and-Fire (RAF) neuron, whose derivation is inspired by biophysical neural modeling. While reflecting further biological plausibility, the RAF neuron is also analytically tractable, and thus may be implemented within neural networks. In the following thesis, we provide a brief overview of the different approaches that have been adopted towards comprehending the properties of nerve cells, along with the framework under which our specific neuron model relates to the field of neuronal modeling. Subsequently, we explore some of the time-dependent neurocomputational capabilities of the RAF neuron, and we utilize the model to classify logic gates, and solve the classic XOR problem. Finally we explore how the resonate-and-fire neuron may be implemented within neural networks, and how such a network could be adapted through the temporal backpropagation algorithm.

Self-organized phase transitions in neural networks as a neural mechanism of information processing.

Transitions between dynamically stable activity patterns imposed on an associative neural network are shown to be induced by self-organized infinitesimal changes in synaptic connection strength and to be a kind of phase transition. A key event for the neural process of information processing in a population coding scheme is transition between the activity patterns encoding usual entities. We propose that the infinitesimal and short-term synaptic changes based on the Hebbian learning rule are the driving force for the transition. The phase transition between the following two dynamical stable states is studied in detail, the state where the firing pattern is changed temporally so as to itinerate among several patterns and the state where the firing pattern is fixed to one of several patterns. The phase transition from the pattern itinerant state to a pattern fixed state may be induced by the Hebbian learning process under a weak input relevant to the fixed pattern. The reverse transition may be induced by the Hebbian unlearning process without input. The former transition is considered as recognition of the input stimulus, while the latter is considered as clearing of the used input data to get ready for new input. To ensure that information processing based on the phase transition can be made by the infinitesimal and short-term synaptic changes, it is absolutely necessary that the network always stays near the critical state corresponding to the phase transition point.

Freeway travel time estimation and prediction using dynamic neural networks

Providing transportation system operators and travelers with accurate travel time information allows them to make more informed decisions, yielding benefits for individual travelers and for the entire transportation system. Most existing advanced traveler information systems (ATIS) and advanced traffic management systems (ATMS) use instantaneous travel time values estimated based on the current measurements, assuming that traffic conditions remain constant in the near future. For more effective applications, it has been proposed that ATIS and ATMS should use travel times predicted for short-term future conditions rather than instantaneous travel times measured or estimated for current conditions. ^ This dissertation research investigates short-term freeway travel time prediction using Dynamic Neural Networks (DNN) based on traffic detector data collected by radar traffic detectors installed along a freeway corridor. DNN comprises a class of neural networks that are particularly suitable for predicting variables like travel time, but has not been adequately investigated for this purpose. Before this investigation, it was necessary to identifying methods for data imputation to account for missing data usually encountered when collecting data using traffic detectors. It was also necessary to identify a method to estimate the travel time on the freeway corridor based on data collected using point traffic detectors. A new travel time estimation method referred to as the Piecewise Constant Acceleration Based (PCAB) method was developed and compared with other methods reported in the literatures. The results show that one of the simple travel time estimation methods (the average speed method) can work as well as the PCAB method, and both of them out-perform other methods. This study also compared the travel time prediction performance of three different DNN topologies with different memory setups. The results show that one DNN topology (the time-delay neural networks) out-performs the other two DNN topologies for the investigated prediction problem. This topology also performs slightly better than the simple multilayer perceptron (MLP) neural network topology that has been used in a number of previous studies for travel time prediction.^

Gesture Recognition Using Neural Networks Based on HW/SW Cosimulation Platform

Hardware/software (HW/SW) cosimulation integrates software simulation and hardware simulation simultaneously. Usually, HW/SW co-simulation platform is used to ease debugging and verification for very large-scale integration (VLSI) design. To accelerate the computation of the gesture recognition technique, an HW/SW implementation using field programmable gate array (FPGA) technology is presented in this paper. The major contributions of this work are: (1) a novel design of memory controller in the Verilog Hardware Description Language (Verilog HDL) to reduce memory consumption and load on the processor. (2) The testing part of the neural network algorithm is being hardwired to improve the speed and performance. The American Sign Language gesture recognition is chosen to verify the performance of the approach. Several experiments were carried out on four databases of the gestures (alphabet signs A to Z). (3) The major benefit of this design is that it takes only few milliseconds to recognize the hand gesture which makes it computationally more efficient.