What is the neural representation of a speech code as it evolves in time? A neural model simulates data concerning segregation and integration of phonetic percepts. Hearing two phonetically related stops in a VC-CV pair (V = vowel; C = consonant) requires 150 ms more closure time than hearing two phonetically different stops in a VC,-C2V pair. Closure time also varies with long-term stimulus rate. The model simulates rate-dependent category boundaries that emerge from feedback: interactions between a working memory for short-term storage of phonetic items and a list categorization network for grouping sequences of items. The conscious speech code is a resonant wave. It emerges after bottom-up signals from the working memory select list chunks which read out top-down expectations that amplify and focus attention on consistent working memory items. In VCi-C2V pairs, resonance is reset by mismatch of Cj with the C, expectation. In VC-CV pairs, resonance prolongs a repeated C. What is the nature of the process that converts brain events into behavioral percepts? An answer to this question is needed in order to understand how the brain controls behavior and how the brain is, in turn, shaped by environmental feedback that is experienced on the behavioral level. The nature of this connection also needs to be understood in order to develop neurally plausible connectionist models. Without it, a correct linking hypothesis cannot be developed between psychological data and the brain mechanisms from which they are generated.

This paper presents a new method for automatic recognition of cancerous tissues from an image of a microscopic section. Based on the shape and the size analysis of the observed cells, this method provides the physician with nonsubjective numerical values for four criteria of malignancy. This automatic approach is based on mathematical morphology, and more specifically on the use of Geodesy. This technique is used first to remove the background noise from the image and then to operate a segmentation of the nuclei of the cells and an analysis of their shape, their size and their texture. From the values of the extracted criteria, an automatic classification of the image (cancerous or not) is finally operated.

this reportedly improved the learning. And still another important contribution in this work was a method for representing recursive structures -- by means of symbolic transformation of any tree structure into a binary tree, which can easily be transformed to a sequence. Those two operations are reversible,

Abstract — In this paper, we study the problem of subtle signal discoveries in unaligned DNA and protein sequences. Motifs, also known as approximate common substrings, are good examples of subtle signals in DNA and protein sequences. The problem of motif identification in DNA and protein sequences has been studied for many years in the literature. Major hurdles at this point include computational complexity and reliability of the searching algorithms. We will develop a self-organizing neural network for solving the problem of motif identification in DNA and protein sequences. Our network contains several layers with each layer performing classifications at different level. The top layer divide the input space into a small number of regions and the bottom layer classifies all input patterns into motifs and non-motif patterns. Depending on the number of input patterns to be classified, several layers between the top layer and the bottom layer are needed to perform intermediate classification. We maintain a low computational complexity through the use of the layered structure so that each pattern’s classification is performed with respect to a small subspace of the whole input space. We also maintain a high reliability using our self-organizing neural network since the network will grow as needed to make sure all input patterns are considered and are given the same amount of attention. Finally, simulation results show that our algorithm significantly outperforms existing algorithms, especially in the reliability aspect. Our algorithm can identify motifs with higher accuracy than existing algorithms.

this paper we first formulate the problem of object labelling and classification on firm mathematical foundations, within the framework of probabilistic relaxation and then we map it onto the conventional architecture of a multilayer perceptron. This way we can give definite interpretation to the weights, response functions and nodes of the system with specific guidance concerning the choice of the various functions and parameters. Further, we end up with a system which requires very few samples for training, thus emulating the human vision system in that respect.

In this new informative era, data and information is the most important asset to the organizations. A large amount of money and manpower have been spent in data gathering, data entry, and storage every year. In Malaysia, data gathering is still largely done through manually-filled forms. This data is then entered and stored into databases in government and private organisations manually. Such mode of data entry and storage requires a lot of manpower and is time consuming. At the Centre for Artificial Intelligence and Robotics (CAIRO) of Universiti Teknologi Malaysia, research is being carried out to design a system for automated data entry of handwritten-filled forms. The system consists of a high-speed scanner with an auto-feeder and a computer. In the first phase a software is developed that allows the user to design the template of existing forms such that only the regions of interests are captured. The next phase involved the design of a software to capture handwritten characters in the regions of interest through the scanned forms. Image processing techniques are then used to filter and improve the image of the scanned handwritten characters before they are recognized using a neural network algorithm. Once the characters are identified and verified they are automatically stored into a database. This system can be used efficiently in many organizations that involves gathering and processing of a large number of data such as the National Registration Department, Survey Research Malaysia, Kementerian Pendidikan and Lembaga Hasil Dalam Negeri.

This work describes AppART, an ART-based low parameterized neural model that incrementally approximates continuous-valued multidimensional functions from noisy data using biologically plausible processes. AppART performs a higher-order Nadaraya-Watson regression and can be interpreted as a fuzzy system. Some benchmark problems are solved in order to study AppART from an application point of view and to compare its results with the ones obtained from other models.

Abstract — In this paper, we study the problem of motif discoveries in unaligned DNA and protein sequences. The problem of motif identification in DNA and protein sequences has been studied for many years in the literature. Major hurdles at this point include computational complexity and reliability of the search algorithms. We propose a self-organizing neural network structure for solving the problem of motif identification in DNA and protein sequences. Our network contains several layers with each layer performing classifications at different levels. The top layer divides the input space into a small number of regions and the bottom layer classifies all input patterns into motifs and non-motif patterns. Depending on the number of input patterns to be classified, several layers between the top layer and the bottom layer are needed to perform intermediate classifications. We maintain a low computational complexity through the use of the layered structure so that each pattern’s classification is performed with respect to a small subspace of the whole input space. Our self-organizing neural network will grow as needed (e.g., when more motif patterns are classified). It will give the same amount of attention to each input pattern and it will not omit any potential motif patterns. Finally, simulation results show that our algorithm outperforms existing algorithms in certain aspects. In particular, simulation results show that our algorithm can identify motifs with more mutations than existing algorithms and our algorithm works well for long DNA sequences as well. Index Terms — DNA sequences, motif finding, neural networks, protein sequences, self-organization, subtle signals. I.

We present a software retrieval scheme based on textual documentation written in natural language. The distinguishing feature of this approach is to use the fuzziness inherent in natural language utterances as a feature to smoothen differences of descriptions of like concepts made by different individuals. The theoretical basis of this approach, systemic functional theory, is adopted from linguistic research. Concepts thus obtained are related by means of fuzzy sets. 1.

HIS work proposes to investigate the application of neural