BOLTZMANN MACHINES FOR SPEECH RECOGNITION.

Boltzmann machines offer a new and exciting approach to automatic speech recognition, and provide a rigorous mathematical formalism for parallel computing arrays. In this paper we briefly summarize Boltzmann machine theory, and present results showing their ability to recognize both static and time-varying speech patterns. A machine with 2000 units was able to distinguish between the 11 steady-state vowels in English with an accuracy of 85%. The stability of the learning algorithm and methods of preprocessing and coding speech data before feeding it to the machine are also discussed. A new type of unit called a carry input unit, which involves a type of state-feedback, was developed for the processing of time-varying patterns and this was tested on a few short sentences. Use is made of the implications of recent work into associative memory, and the modelling of neural arrays to suggest a good configuration of Boltzmann machines for this sort of pattern recognition.

Achieving robust face recognition from video by combining a weak photometric model and a learnt generic face invariant

In spite of over two decades of intense research, illumination and pose invariance remain prohibitively challenging aspects of face recognition for most practical applications. The objective of this work is to recognize faces using video sequences both for training and recognition input, in a realistic, unconstrained setup in which lighting, pose and user motion pattern have a wide variability and face images are of low resolution. The central contribution is an illumination invariant, which we show to be suitable for recognition from video of loosely constrained head motion. In particular there are three contributions: (i) we show how a photometric model of image formation can be combined with a statistical model of generic face appearance variation to exploit the proposed invariant and generalize in the presence of extreme illumination changes; (ii) we introduce a video sequence re-illumination algorithm to achieve fine alignment of two video sequences; and (iii) we use the smoothness of geodesically local appearance manifold structure and a robust same-identity likelihood to achieve robustness to unseen head poses. We describe a fully automatic recognition system based on the proposed method and an extensive evaluation on 323 individuals and 1474 video sequences with extreme illumination, pose and head motion variation. Our system consistently achieved a nearly perfect recognition rate (over 99.7% on all four databases). © 2012 Elsevier Ltd All rights reserved.

Short and long peptidoglycan recognition proteins (PGRPs) in zebrafish, with findings of multiple PGRP homologs in teleost fish

Peptidoglycan recognition protein (PGRP) specifically binds to peptidoglycan and is considered to be one of the pattern recognition proteins in the innate immunity of insect and mammals. Using a database mining approach and RT-PCR, multiple peptidoglycan recognition protein (PGRP) like genes have been discovered in fish including zebrafish Danio rerio, Japanese pufferfish TakiFugu rubripes and spotted green pufferfish Tetraodon nigroviridis. They share the common features of those PGRPs in arthropod and mammals, by containing a conserved PGRP domain. Based on the predicted structures, the identified zebrafish PGRP homologs resemble short and long PGRP members in arthropod and mammals. The identified PGRP genes in T. nigroviridis and TakiFugu rubripes resemble the long PGRPs, and the short PGRP genes have not been found in T. nigroviridis and TakiFugu rubripes databases. Computer modelling of these molecules revealed the presence of three alpha-helices and five or six beta-strands in all fish PGRPs reported in the present study. The long PGRP in teleost fish have multiple alternatively spliced forms, and some of the identified spliced variants, e.g., tnPGRP-L3 and tnPGRP-L4 (in: Tetraodon nigroviridis), exhibited no characters present in the PGRP homologs domain. The coding regions of zfPGRP6 (zf: zebrafish), zfPGRP2-A, zfPGRP2-B and zfPGRP-L contain five exons and four introns; however, the other PGRP-like genes including zfPGRPSC1a, zfPGRPSC2, tnPGRP-L1-, tnPGRP-L2 and frPGRP-L (fr: Takifugu rubripes) contain four exons and three introns. In zebrafish, long and short PGRP genes identified are located in different chromosomes, and an unknown locus containing another long PGRP-like gene has also been found in zebrafish, demonstrating that multiple PGRP loci may be present in fish. In zebrafish, the constitutive expressions of zfPGRP-L, zfPGRP-6 and zfPGRP-SC during ontogeny from unfertilized eggs to larvae, in different organs of adult, and the inductive expression following stimulation by Flavobacterium columnare, were detected by real-time PCR, but the levels and patterns varied for different PGRP genes, implying that different short and long PGRPs may play different roles in innate immune response. (c) 2007 Elsevier Ltd. All rights reserved.

A Cancer Recognition Method Based on DNA Microarray

The accurate cancer classification is of great importance in clinical treatment. Recently, the DNA microarray technology provides a promising approach to the diagnosis and prognosis of cancer types. However, it has no perfect method for the multiclass classification problem. The difficulty lies in the fact that the data are of high dimensionality with small sample size. This paper proposed an automatic classification method of multiclass cancers based on Biomimetic pattern recognition (BPR). To the public GCM data set, the average correct classification rate reaches 80% under the condition that the correct rejection rate is 81%.

The application of DBF neural networks for object recognition

On the basis of DBF nets proposed by Wang Shoujue, the model and properties of DBF neural network were discussed in this paper. When applied in pattern recognition, the algorithm and implement on hardware were presented respectively. We did experiments on recognition of omnidirectionally oriented rigid objects on the same level, using direction basis function neural networks, which acts by the method of covering the high dimensional geometrical distribution of the sample set in the feature space. Many animal and vehicle models (even with rather similar shapes) were recognized omnidirectionally thousands of times. For total 8800 tests, the correct recognition rate is 98.75%, the error rate and the rejection rate are 0.5% and 1.25% respectively. (C) 2003 Elsevier Inc. All rights reserved.

Iris recognition algorithm based on point covering of high-dimensional space and neural network

In this paper, we constructed a Iris recognition algorithm based on point covering of high-dimensional space and Multi-weighted neuron of point covering of high-dimensional space, and proposed a new method for iris recognition based on point covering theory of high-dimensional space. In this method, irises are trained as "cognition" one class by one class, and it doesn't influence the original recognition knowledge for samples of the new added class. The results of experiments show the rejection rate is 98.9%, the correct cognition rate and the error rate are 95.71% and 3.5% respectively. The experimental results demonstrate that the rejection rate of test samples excluded in the training samples class is very high. It proves the proposed method for iris recognition is effective.

A novel face recognition method based on hypersausage neural networks

In this paper, we firstly give the nature of 'hypersausages', study its structure and training of the network, then discuss the nature of it by way of experimenting with ORL face database, and finally, verify its unsurpassable advantages compared with other means.

Hypersausage neural networks and its application in face recognition

In this paper, we firstly give the nature of 'hypersausages', study its structure and training of the network, then discuss the nature of it by way of experimenting with ORL face database, and finally, verify its unsurpassable advantages compared with other means.