Interpretación geométrica de redes neuronales recurrentes discretas mediante grafos completos

El objetivo del presente trabajo de investigación es explorar nuevas técnicas de implementación, basadas en grafos, para las Redes de Neuronas, con el fin de simplificar y optimizar las arquitecturas y la complejidad computacional de las mismas. Hemos centrado nuestra atención en una clase de Red de Neuronas: las Redes de Neuronas Recursivas (RNR), también conocidas como redes de Hopfield. El problema de obtener la matriz sináptica asociada con una RNR imponiendo un determinado número de vectores como puntos fijos, no está en absoluto resuelto, el número de vectores prototipo que pueden ser almacenados en la red, cuando se utiliza la ley de Hebb, es bastante limitado, la red se satura rápidamente cuando se pretende almacenar nuevos prototipos. La ley de Hebb necesita, por tanto, ser revisada. Algunas aproximaciones dirigidas a solventar dicho problema, han sido ya desarrolladas. Nosotros hemos desarrollado una nueva aproximación en la forma de implementar una RNR en orden a solucionar estos problemas. La matriz sináptica es obtenida mediante la superposición de las componentes de los vectores prototipo, sobre los vértices de un Grafo, lo cual puede ser también interpretado como una coloración de dicho grafo. Cuando el periodo de entrenamiento se termina, la matriz de adyacencia del Grafo Resultante o matriz de pesos, presenta ciertas propiedades por las cuales dichas matrices serán llamadas tetraédricas. La energía asociada a cualquier estado de la red es representado por un punto (a,b) de R2. Cada uno de los puntos de energía asociados a estados que disten lo mismo del vector cero está localizado sobre la misma línea de energía de R2. El espacio de vectores de estado puede, por tanto, clasificarse en n clases correspondientes a cada una de las n diferentes distancias que puede tener cualquier vector al vector cero. La matriz (n x n) de pesos puede reducirse a un n-vector; de esta forma, tanto el tiempo de computación como el espacio de memoria requerido par almacenar los pesos, son simplificados y optimizados. En la etapa de recuperación, es introducido un vector de parámetros R2, éste es utilizado para controlar la capacidad de la red: probaremos que lo mayor es la componente a¡, lo menor es el número de puntos fijos pertenecientes a la línea de energía R¡. Una vez que la capacidad de la red ha sido controlada mediante este parámetro, introducimos otro parámetro, definido como la desviación del vector de pesos relativos, este parámetro sirve para disminuir ostensiblemente el número de parásitos. A lo largo de todo el trabajo, hemos ido desarrollando un ejemplo, el cual nos ha servido para ir corroborando los resultados teóricos, los algoritmos están escritos en un pseudocódigo, aunque a su vez han sido implamentados utilizando el paquete Mathematica 2.2., mostrándolos en un volumen suplementario al texto.---ABSTRACT---The aim of the present research is intended to explore new specifícation techniques of Neural Networks based on Graphs to be used in the optimization and simplification of Network Architectures and Computational Complexhy. We have focused our attention in a, well known, class of Neural Networks: the Recursive Neural Networks, also known as Hopfield's Neural Networks. The general problem of constructing the synaptic matrix associated with a Recursive Neural Network imposing some vectors as fixed points is fer for completery solved, the number of prototype vectors (learning patterns) which can be stored by Hebb's law is rather limited and the memory will thus quickly reach saturation if new prototypes are continuously acquired in the course of time. Hebb's law needs thus to be revised in order to allow new prototypes to be stored at the expense of the older ones. Some approaches related with this problem has been developed. We have developed a new approach of implementing a Recursive Neural Network in order to sob/e these kind of problems, the synaptic matrix is obtained superposing the components of the prototype vectors over the vértices of a Graph which may be interpreted as a coloring of the Graph. When training is finished the adjacency matrix of the Resulting Graph or matrix of weights presents certain properties for which it may be called a tetrahedral matrix The energy associated to any possible state of the net is represented as a point (a,b) in R2. Every one of the energy points associated with state-vectors having the same Hamming distance to the zero vector are located over the same energy Une in R2. The state-vector space may be then classified in n classes according to the n different possible distances firom any of the state-vectors to the zero vector The (n x n) matrix of weights may also be reduced to a n-vector of weights, in this way the computational time and the memory space required for obtaining the weights is optimized and simplified. In the recall stage, a parameter vectora is introduced, this parameter is used for controlling the capacity of the net: it may be proved that the bigger is the r, component of J, the lower is the number of fixed points located in the r¡ energy line. Once the capacity of the net has been controlled by the ex parameter, we introduced other parameter, obtained as the relative weight vector deviation parameter, in order to reduce the number of spurious states. All along the present text, we have also developed an example, which serves as a prove for the theoretical results, the algorithms are shown in a pseudocode language in the text, these algorithm so as the graphics have been developed also using the Mathematica 2.2. mathematical package which are shown in a supplementary volume of the text.

A class of self-stabilizing MCA learning algorithms

In this letter, we propose a class of self-stabilizing learning algorithms for minor component analysis (MCA), which includes a few well-known MCA learning algorithms. Self-stabilizing means that the sign of the weight vector length change is independent of the presented input vector. For these algorithms, rigorous global convergence proof is given and the convergence rate is also discussed. By combining the positive properties of these algorithms, a new learning algorithm is proposed which can improve the performance. Simulations are employed to confirm our theoretical results.

Threshold-induced phase transitions in perceptrons

Error rates of a Boolean perceptron with threshold and either spherical or Ising constraint on the weight vector are calculated for storing patterns from biased input and output distributions derived within a one-step replica symmetry breaking (RSB) treatment. For unbiased output distribution and non-zero stability of the patterns, we find a critical load, α p, above which two solutions to the saddlepoint equations appear; one with higher free energy and zero threshold and a dominant solution with non-zero threshold. We examine this second-order phase transition and the dependence of α p on the required pattern stability, κ, for both one-step RSB and replica symmetry (RS) in the spherical case and for one-step RSB in the Ising case.

Applying SVMs and weight-based factor analysis to unsupervised adaptation for speaker verification

This paper presents an extended study on the implementation of support vector machine(SVM) based speaker verification in systems that employ continuous progressive model adaptation using the weight-based factor analysis model. The weight-based factor analysis model compensates for session variations in unsupervised scenarios by incorporating trial confidence measures in the general statistics used in the inter-session variability modelling process. Employing weight-based factor analysis in Gaussian mixture models (GMM) was recently found to provide significant performance gains to unsupervised classification. Further improvements in performance were found through the integration of SVM-based classification in the system by means of GMM supervectors. This study focuses particularly on the way in which a client is represented in the SVM kernel space using single and multiple target supervectors. Experimental results indicate that training client SVMs using a single target supervector maximises performance while exhibiting a certain robustness to the inclusion of impostor training data in the model. Furthermore, the inclusion of low-scoring target trials in the adaptation process is investigated where they were found to significantly aid performance.

Predicting residue-wise contact orders in proteins by support vector regression

Background The residue-wise contact order (RWCO) describes the sequence separations between the residues of interest and its contacting residues in a protein sequence. It is a new kind of one-dimensional protein structure that represents the extent of long-range contacts and is considered as a generalization of contact order. Together with secondary structure, accessible surface area, the B factor, and contact number, RWCO provides comprehensive and indispensable important information to reconstructing the protein three-dimensional structure from a set of one-dimensional structural properties. Accurately predicting RWCO values could have many important applications in protein three-dimensional structure prediction and protein folding rate prediction, and give deep insights into protein sequence-structure relationships. Results We developed a novel approach to predict residue-wise contact order values in proteins based on support vector regression (SVR), starting from primary amino acid sequences. We explored seven different sequence encoding schemes to examine their effects on the prediction performance, including local sequence in the form of PSI-BLAST profiles, local sequence plus amino acid composition, local sequence plus molecular weight, local sequence plus secondary structure predicted by PSIPRED, local sequence plus molecular weight and amino acid composition, local sequence plus molecular weight and predicted secondary structure, and local sequence plus molecular weight, amino acid composition and predicted secondary structure. When using local sequences with multiple sequence alignments in the form of PSI-BLAST profiles, we could predict the RWCO distribution with a Pearson correlation coefficient (CC) between the predicted and observed RWCO values of 0.55, and root mean square error (RMSE) of 0.82, based on a well-defined dataset with 680 protein sequences. Moreover, by incorporating global features such as molecular weight and amino acid composition we could further improve the prediction performance with the CC to 0.57 and an RMSE of 0.79. In addition, combining the predicted secondary structure by PSIPRED was found to significantly improve the prediction performance and could yield the best prediction accuracy with a CC of 0.60 and RMSE of 0.78, which provided at least comparable performance compared with the other existing methods. Conclusion The SVR method shows a prediction performance competitive with or at least comparable to the previously developed linear regression-based methods for predicting RWCO values. In contrast to support vector classification (SVC), SVR is very good at estimating the raw value profiles of the samples. The successful application of the SVR approach in this study reinforces the fact that support vector regression is a powerful tool in extracting the protein sequence-structure relationship and in estimating the protein structural profiles from amino acid sequences.

Socioeconomic inequalities in weight status among mid-aged adults : the contribution of perceptions of weight status and weight-control behaviours

Background Socioeconomically-disadvantaged adults in developed countries experience a higher prevalence of a number of chronic diseases, such as cardiovascular disease, type 2 diabetes, osteoarthritis and some forms of cancer. Overweight and obesity are major risk factors for these diseases. Lower socioeconomic groups have a greater prevalence of overweight and obesity and this may contribute to their higher morbidity and mortality. International studies suggest that socioeconomic groups may differ in their self-perceptions of weight status and their engagement in weightcontrol behaviours (WCBs). Research has shown that lower socioeconomic adults are more likely to underestimate their weight status, and are less likely to engage in WCBs. This may contribute (in part) to the marked inequalities in weight status observed at the population level. There are few, and somewhat limited, Australian studies that have examined the types of weight-control strategies people adopt, the barriers to their weight control, the determinants of their perceived weight status and WCBs. Furthermore, there are no known Australian studies that have examined socioeconomic differences in these factors to better understand the reasons for socioeconomic inequalities in weight status. Hence, the overall aim of this Thesis is to examine why socioeconomically-disadvantaged group experience a greater prevalence of overweight and obesity than their more-advantaged counterparts. Methods This Thesis used data from two sources. Men and women aged 45 to 60 years were examined from both data source. First, the longitudinal Australian Diabetes, Obesity and Lifestyle (AusDiab) Study were used to advance our knowledge and understanding of socioeconomic differences in weight change, perceived weight status and WCBs. A total of 2753 participants with measured weights at both baseline (1999-2000) and follow-up (2004-2005) were included in the analyses. Percent weight change over the five-year interval was calculated and perceived weight status, WCBs and highest attained education were collected at baseline. Second, the Candidate conducted a postal questionnaire from 1013 Brisbane residents (69.8 % response rate) to investigate the relationship between socioeconomic position, determinants of perceived weight status, WCBs, and barriers and reasons to weight control. A test-retest reliability study was conducted to determine the reliability of the new measures used in the questionnaire. Most new measures had substantial to almost perfect reliability when considering either kappa coefficient or crude agreement. Results The findings from the AusDiab Study (accepted for publication in the Australian and New Zealand Journal of Public Health) showed that low-educated men and women were more likely to be obese at baseline compared to their higheducated respondents (O.R. = 1.97, 95 % C.I. = 1.30-2.98 and O.R. = 1.52, 95 % C.I. = 1.03-2.25, respectively). Over the five year follow-up period (1999-2000 to 2004- 05) there were no socioeconomic differences in weight change among men, however socioeconomically-disadvantaged women had greater weight gains. Participants perceiving themselves as overweight gained less weight than those who saw themselves as underweight or normal weight. There was no relationship between engaging in WCBs and five-year weight change. The postal questionnaire data showed that socioeconomically-disadvantaged groups were less likely to engage in WCBs. If they did engage in weight control, they were less likely to adopt exercise strategies, including moderate and vigorous physical activities but were more likely to decrease their sitting time to control their weight. Socioeconomically-disadvantaged adults reported more barriers to weight control; such as perceiving weight loss as expensive, requiring a lot of cooking skills, not being a high priority and eating differently from other people in the household. These results have been accepted for publication in Public Health Nutrition. The third manuscript (under review in Social Science and Medicine) examined socioeconomic differences in determinants of perceived weight status and reasons for weight control. The results showed that lower socioeconomic adults were more likely to specify the following reasons for weight control: they considered themselves to be too heavy, for occupational requirements, on recommendation from their doctor, family members or friends. Conversely, high-income adults were more likely to report weight control to improve their physical condition or to look more attractive compared with those on lower-incomes. There were few socioeconomic differences in the determinants of perceived weight status. Conclusions Education inequalities in overweight/obesity among men and women may be due to mis-perceptions of weight status; overweight or obese individuals in loweducated groups may not perceive their weight as problematic and therefore may not pay attention to their energy-balance behaviours. Socioeconomic groups differ in WCBs, and their reasons and perceived barriers to weight control. Health promotion programs should encourage weight control among lower socioeconomic groups. More specifically, they should encourage the engagement of physical activity or exercise and dietary strategies among disadvantaged groups. Furthermore, such programs should address potential barriers for weight control that disadvantaged groups may encounter. For example, disadvantaged groups perceive that weight control is expensive, requires cooking skills, not a high priority and eating differently from other people in the household. Lastly, health promotion programs and policies aimed at reducing overweight and obesity should be tailored to the different reasons and motivations to weight control experienced by different socioeconomic groups. Weight-control interventions targeted at higher socioeconomic groups should use improving physical condition and attractiveness as motivational goals; while, utilising social support may be more effective for encouraging weight control among lower socioeconomic groups.

An investigation into the use of human papillomavirus type 16 virus-like particles as a delivery vector system for foreign proteins: N- and C-terminal fusion of GFP to the L1 and L2 capsid proteins

Development of vaccine strategies against human papillomavirus (HPV), which causes cervical cancer, is a priority. We investigated the use of virus-like particles (VLPs) of the most prevalent type, HPV-16, as carriers of foreign proteins. Green fluorescent protein (GFP) was fused to the N or C terminus of both L1 and L2, with L2 chimeras being co-expressed with native L1. Purified chimaeric VLPs were comparable in size (∼55 nm) to native HPV VLPs. Conformation-specific monoclonal antibodies (Mabs) bound to the VLPs, thereby indicating that they possibly retain their antigenicity. In addition, all of the VLPs encapsidated DNA in the range of 6-8 kb. © 2007 Springer-Verlag.

Genome segment 5 of rice ragged stunt virus encodes a virion protein

The complete nucleotide sequence of the genome segment 5 (S5) of a Thai isolate of rice ragged stunt virus (RRSV) was determined. The 2682 nucleotide sequence contains a single long open reading frame capable of encoding a polypeptide with a molecular mass of ~91 kDa. Polypeptides encoded by various truncated cDNAs of S5 were expressed using the pGEX fusion protein vector and the highest level of fusion protein was obtained from a construct encoding a hydrophilic region of S5 protein. Antibodies raised against this fusion protein recognized a minor polypeptide, with a molecular mass of ~ 91 kDa, that was present in purified preparations of RRSV particles, infected insect vectors and infected rice plants. This indicates that RRSV S5 encodes a minor structural protein. Comparing the RRSV S5 sequence with sequences of other reo-viruses did not reveal any significant sequence similarities.

DS-VBF : dual sink vector-based routing protocol for underwater wireless sensor network

Underwater wireless sensor networks (UWSNs) have become the seat of researchers' attention recently due to their proficiency to explore underwater areas and design different applications for marine discovery and oceanic surveillance. One of the main objectives of each deployed underwater network is discovering the optimized path over sensor nodes to transmit the monitored data to onshore station. The process of transmitting data consumes energy of each node, while energy is limited in UWSNs. So energy efficiency is a challenge in underwater wireless sensor network. Dual sinks vector based forwarding (DS-VBF) takes both residual energy and location information into consideration as priority factors to discover an optimized routing path to save energy in underwater networks. The modified routing protocol employs dual sinks on the water surface which improves network lifetime. According to deployment of dual sinks, packet delivery ratio and the average end to end delay are enhanced. Based on our simulation results in comparison with VBF, average end to end delay reduced more than 80%, remaining energy increased 10%, and the increment of packet reception ratio was about 70%.

Low birth weight in MZ twins discordant for birth weight is associated with shorter telomere length and lower IQ, but not anxiety/depression in later life

Shorter telomere length (TL) has found to be associated with lower birth weight and with lower cognitive ability and psychiatric disorders. However, the direction of causation of these associations and the extent to which they are genetically or environmentally mediated are unclear. Within-pair comparisons of monozygotic (MZ) and dizygotic (DZ) twins can throw light on these questions. We investigated correlations of within pair differences in telomere length, IQ, and anxiety/depression in an initial sample from Brisbane (242 MZ pairs, 245 DZ same sex (DZSS) pairs) and in replication samples from Amsterdam (514 MZ pairs, 233 DZSS pairs) and Melbourne (19 pairs selected for extreme high or low birth weight difference). Intra-pair differences of birth weight and telomere length were significantly correlated in MZ twins, but not in DZSS twins. Greater intra-pair differences of telomere length were observed in the 10% of MZ twins with the greatest difference in birth weight compared to the bottom 90% in both samples and also in the Melbourne sample. Intra-pair differences of telomere length and IQ, but not of TL and anxiety/depression, were correlated in MZ twins, and to a smaller extent in DZSS twins. Our findings suggest that the same prenatal effects that reduce birth weight also influence telomere length in MZ twins. The association between telomere length and IQ is partly driven by the same prenatal effects that decrease birth weight.

OCR Prediction Using Support Vector Machine Based on Piezocone Data

The determination of the overconsolidation ratio (OCR) of clay deposits is an important task in geotechnical engineering practice. This paper examines the potential of a support vector machine (SVM) for predicting the OCR of clays from piezocone penetration test data. SVM is a statistical learning theory based on a structural risk minimization principle that minimizes both error and weight terms. The five input variables used for the SVM model for prediction of OCR are the corrected cone resistance (qt), vertical total stress (sigmav), hydrostatic pore pressure (u0), pore pressure at the cone tip (u1), and the pore pressure just above the cone base (u2). Sensitivity analysis has been performed to investigate the relative importance of each of the input parameters. From the sensitivity analysis, it is clear that qt=primary in situ data influenced by OCR followed by sigmav, u0, u2, and u1. Comparison between SVM and some of the traditional interpretation methods is also presented. The results of this study have shown that the SVM approach has the potential to be a practical tool for determination of OCR.

Vector evaluated particle swarm optimization (VEPSO) for multi-objective design optimization of composite structures

We present a generic method/model for multi-objective design optimization of laminated composite components, based on vector evaluated particle swarm optimization (VEPSO) algorithm. VEPSO is a novel, co-evolutionary multi-objective variant of the popular particle swarm optimization algorithm (PSO). In the current work a modified version of VEPSO algorithm for discrete variables has been developed and implemented successfully for the, multi-objective design optimization of composites. The problem is formulated with multiple objectives of minimizing weight and the total cost of the composite component to achieve a specified strength. The primary optimization variables are - the number of layers, its stacking sequence (the orientation of the layers) and thickness of each layer. The classical lamination theory is utilized to determine the stresses in the component and the design is evaluated based on three failure criteria; failure mechanism based failure criteria, Maximum stress failure criteria and the Tsai-Wu failure criteria. The optimization method is validated for a number of different loading configurations - uniaxial, biaxial and bending loads. The design optimization has been carried for both variable stacking sequences, as well fixed standard stacking schemes and a comparative study of the different design configurations evolved has been presented. (C) 2007 Elsevier Ltd. All rights reserved.

MPI-based parallel synchronous vector evaluated particle swarm optimization for multi-objective design optimization of composite structures

This paper presents a decentralized/peer-to-peer architecture-based parallel version of the vector evaluated particle swarm optimization (VEPSO) algorithm for multi-objective design optimization of laminated composite plates using message passing interface (MPI). The design optimization of laminated composite plates being a combinatorially explosive constrained non-linear optimization problem (CNOP), with many design variables and a vast solution space, warrants the use of non-parametric and heuristic optimization algorithms like PSO. Optimization requires minimizing both the weight and cost of these composite plates, simultaneously, which renders the problem multi-objective. Hence VEPSO, a multi-objective variant of the PSO algorithm, is used. Despite the use of such a heuristic, the application problem, being computationally intensive, suffers from long execution times due to sequential computation. Hence, a parallel version of the PSO algorithm for the problem has been developed to run on several nodes of an IBM P720 cluster. The proposed parallel algorithm, using MPI's collective communication directives, establishes a peer-to-peer relationship between the constituent parallel processes, deviating from the more common master-slave approach, in achieving reduction of computation time by factor of up to 10. Finally we show the effectiveness of the proposed parallel algorithm by comparing it with a serial implementation of VEPSO and a parallel implementation of the vector evaluated genetic algorithm (VEGA) for the same design problem. (c) 2012 Elsevier Ltd. All rights reserved.

Efficient Dendrimer-DNA Complexation and Gene Delivery Vector Properties of Nitrogen-Core Poly(propyl ether imine) Dendrimer in Mammalian Cells

Dendrimers as vectors for gene delivery were established, primarily by utilizing few prominent dendrimer types so far. We report herein studies of DNA complexation efficacies and gene delivery vector properties of a nitrogen-core poly(propyl ether imine) (PETIM) dendrimer, constituted with 22 tertiary amine internal branches and 24 primary amines at the periphery. The interaction of the dendrimer with pEGFPDNA was evaluated through UV-vis, circular dichroism (CD) spectral studies, ethidium bromide fluorescence emission quenching, thermal melting, and gel retardation assays, from which most changes to DNA structure during complexation was found to occur at a weight ratio of dendrimer:DNA similar to 2:1. The zeta potential measurements further confirmed this stoichiometry at electroneutrality. The structure of a DNA oligomer upon dendrimer complexation was simulated through molecular modeling and the simulation showed that the dendrimer enfolded DNA oligomer along both major and minor grooves, without causing DNA deformation, in 1:1 and 2:1 dendrimer-to-DNA complexes. Atomic force microscopy (AFM) studies on dendrimer-pEGFP DNA complex showed an increase in the average z-height as a result of dendrimers decorating the DNA, without causing a distortion of the DNA structure. Cytotoxicity studies involving five different mammalian cell lines, using 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl-tetrazolium bromide] (MTT) assay, reveal the dendrimer toxicity profile (IC50) values of similar to 400-1000 mu g mL(-1), depending on the cell line tested. Quantitative estimation, using luciferase assay, showed that the gene transfection was at least 100 times higher when compared to poly(ethylene imine) branched polymer, having similar number of cationic sites as the dendrimer. The present study establishes the physicochemical behavior of new nitrogen-core PETIM dendrimer-DNA complexes, their lower toxicities, and efficient gene delivery vector properties.

Low Molecular Weight Chitosan (LMWC)-based Polyplexes for pDNA Delivery: From Bench to Bedside

Non-viral gene delivery vectors are emerging as a safer alternative to viral vectors. Among natural polymers, chitosan (Ch) is the most studied one, and low molecular weight Ch, specifically, presents a wide range of advantages for non-viral pDNA delivery. It is crucial to determine the best process for the formation of Low Molecular Weight Chitosan (LMWC)-pDNA complexes and to characterize their physicochemical properties to better understand their behavior once the polyplexes are administered. The transfection efficiency of Ch based polyplexes is relatively low. Therefore, it is essential to understand all the transfection process, including the cellular uptake, endosomal escape and nuclear import, together with the parameters involved in the process to improve the design and development of the non-viral vectors. The aim of this review is to describe the formation and characterization of LMWC based polyplexes, the in vitro transfection process and finally, the in vivo applications of LMWC based polyplexes for gene therapy purposes.