Advances in scaling deep learning algorithms

Les algorithmes d'apprentissage profond forment un nouvel ensemble de méthodes puissantes pour l'apprentissage automatique. L'idée est de combiner des couches de facteurs latents en hierarchies. Cela requiert souvent un coût computationel plus elevé et augmente aussi le nombre de paramètres du modèle. Ainsi, l'utilisation de ces méthodes sur des problèmes à plus grande échelle demande de réduire leur coût et aussi d'améliorer leur régularisation et leur optimization. Cette thèse adresse cette question sur ces trois perspectives. Nous étudions tout d'abord le problème de réduire le coût de certains algorithmes profonds. Nous proposons deux méthodes pour entrainer des machines de Boltzmann restreintes et des auto-encodeurs débruitants sur des distributions sparses à haute dimension. Ceci est important pour l'application de ces algorithmes pour le traitement de langues naturelles. Ces deux méthodes (Dauphin et al., 2011; Dauphin and Bengio, 2013) utilisent l'échantillonage par importance pour échantilloner l'objectif de ces modèles. Nous observons que cela réduit significativement le temps d'entrainement. L'accéleration atteint 2 ordres de magnitude sur plusieurs bancs d'essai. Deuxièmement, nous introduisont un puissant régularisateur pour les méthodes profondes. Les résultats expérimentaux démontrent qu'un bon régularisateur est crucial pour obtenir de bonnes performances avec des gros réseaux (Hinton et al., 2012). Dans Rifai et al. (2011), nous proposons un nouveau régularisateur qui combine l'apprentissage non-supervisé et la propagation de tangente (Simard et al., 1992). Cette méthode exploite des principes géometriques et permit au moment de la publication d'atteindre des résultats à l'état de l'art. Finalement, nous considérons le problème d'optimiser des surfaces non-convexes à haute dimensionalité comme celle des réseaux de neurones. Tradionellement, l'abondance de minimum locaux était considéré comme la principale difficulté dans ces problèmes. Dans Dauphin et al. (2014a) nous argumentons à partir de résultats en statistique physique, de la théorie des matrices aléatoires, de la théorie des réseaux de neurones et à partir de résultats expérimentaux qu'une difficulté plus profonde provient de la prolifération de points-selle. Dans ce papier nous proposons aussi une nouvelle méthode pour l'optimisation non-convexe.

FPGA-based object detection using classification circuits

Dans l'apprentissage machine, la classification est le processus d’assigner une nouvelle observation à une certaine catégorie. Les classifieurs qui mettent en œuvre des algorithmes de classification ont été largement étudié au cours des dernières décennies. Les classifieurs traditionnels sont basés sur des algorithmes tels que le SVM et les réseaux de neurones, et sont généralement exécutés par des logiciels sur CPUs qui fait que le système souffre d’un manque de performance et d’une forte consommation d'énergie. Bien que les GPUs puissent être utilisés pour accélérer le calcul de certains classifieurs, leur grande consommation de puissance empêche la technologie d'être mise en œuvre sur des appareils portables tels que les systèmes embarqués. Pour rendre le système de classification plus léger, les classifieurs devraient être capable de fonctionner sur un système matériel plus compact au lieu d'un groupe de CPUs ou GPUs, et les classifieurs eux-mêmes devraient être optimisés pour ce matériel. Dans ce mémoire, nous explorons la mise en œuvre d'un classifieur novateur sur une plate-forme matérielle à base de FPGA. Le classifieur, conçu par Alain Tapp (Université de Montréal), est basé sur une grande quantité de tables de recherche qui forment des circuits arborescents qui effectuent les tâches de classification. Le FPGA semble être un élément fait sur mesure pour mettre en œuvre ce classifieur avec ses riches ressources de tables de recherche et l'architecture à parallélisme élevé. Notre travail montre que les FPGAs peuvent implémenter plusieurs classifieurs et faire les classification sur des images haute définition à une vitesse très élevée.

Automatic Image Annotation Using SURF Descriptors

In recent years there is an apparent shift in research from content based image retrieval (CBIR) to automatic image annotation in order to bridge the gap between low level features and high level semantics of images. Automatic Image Annotation (AIA) techniques facilitate extraction of high level semantic concepts from images by machine learning techniques. Many AIA techniques use feature analysis as the first step to identify the objects in the image. However, the high dimensional image features make the performance of the system worse. This paper describes and evaluates an automatic image annotation framework which uses SURF descriptors to select right number of features and right features for annotation. The proposed framework uses a hybrid approach in which k-means clustering is used in the training phase and fuzzy K-NN classification in the annotation phase. The performance of the system is evaluated using standard metrics.

Development of Hierarchical Clustering Techniques for Gridded Data from Mixed Data Sequences

Knowledge discovery in databases is the non-trivial process of identifying valid, novel potentially useful and ultimately understandable patterns from data. The term Data mining refers to the process which does the exploratory analysis on the data and builds some model on the data. To infer patterns from data, data mining involves different approaches like association rule mining, classification techniques or clustering techniques. Among the many data mining techniques, clustering plays a major role, since it helps to group the related data for assessing properties and drawing conclusions. Most of the clustering algorithms act on a dataset with uniform format, since the similarity or dissimilarity between the data points is a significant factor in finding out the clusters. If a dataset consists of mixed attributes, i.e. a combination of numerical and categorical variables, a preferred approach is to convert different formats into a uniform format. The research study explores the various techniques to convert the mixed data sets to a numerical equivalent, so as to make it equipped for applying the statistical and similar algorithms. The results of clustering mixed category data after conversion to numeric data type have been demonstrated using a crime data set. The thesis also proposes an extension to the well known algorithm for handling mixed data types, to deal with data sets having only categorical data. The proposed conversion has been validated on a data set corresponding to breast cancer. Moreover, another issue with the clustering process is the visualization of output. Different geometric techniques like scatter plot, or projection plots are available, but none of the techniques display the result projecting the whole database but rather demonstrate attribute-pair wise analysis

Soft Computing Approach for Optimization of siRNA Efficiency Prediction for Post-transcriptional Gene Silencing

Post-transcriptional gene silencing by RNA interference is mediated by small interfering RNA called siRNA. This gene silencing mechanism can be exploited therapeutically to a wide variety of disease-associated targets, especially in AIDS, neurodegenerative diseases, cholesterol and cancer on mice with the hope of extending these approaches to treat humans. Over the recent past, a significant amount of work has been undertaken to understand the gene silencing mediated by exogenous siRNA. The design of efficient exogenous siRNA sequences is challenging because of many issues related to siRNA. While designing efficient siRNA, target mRNAs must be selected such that their corresponding siRNAs are likely to be efficient against that target and unlikely to accidentally silence other transcripts due to sequence similarity. So before doing gene silencing by siRNAs, it is essential to analyze their off-target effects in addition to their inhibition efficiency against a particular target. Hence designing exogenous siRNA with good knock-down efficiency and target specificity is an area of concern to be addressed. Some methods have been developed already by considering both inhibition efficiency and off-target possibility of siRNA against agene. Out of these methods, only a few have achieved good inhibition efficiency, specificity and sensitivity. The main focus of this thesis is to develop computational methods to optimize the efficiency of siRNA in terms of “inhibition capacity and off-target possibility” against target mRNAs with improved efficacy, which may be useful in the area of gene silencing and drug design for tumor development. This study aims to investigate the currently available siRNA prediction approaches and to devise a better computational approach to tackle the problem of siRNA efficacy by inhibition capacity and off-target possibility. The strength and limitations of the available approaches are investigated and taken into consideration for making improved solution. Thus the approaches proposed in this study extend some of the good scoring previous state of the art techniques by incorporating machine learning and statistical approaches and thermodynamic features like whole stacking energy to improve the prediction accuracy, inhibition efficiency, sensitivity and specificity. Here, we propose one Support Vector Machine (SVM) model, and two Artificial Neural Network (ANN) models for siRNA efficiency prediction. In SVM model, the classification property is used to classify whether the siRNA is efficient or inefficient in silencing a target gene. The first ANNmodel, named siRNA Designer, is used for optimizing the inhibition efficiency of siRNA against target genes. The second ANN model, named Optimized siRNA Designer, OpsiD, produces efficient siRNAs with high inhibition efficiency to degrade target genes with improved sensitivity-specificity, and identifies the off-target knockdown possibility of siRNA against non-target genes. The models are trained and tested against a large data set of siRNA sequences. The validations are conducted using Pearson Correlation Coefficient, Mathews Correlation Coefficient, Receiver Operating Characteristic analysis, Accuracy of prediction, Sensitivity and Specificity. It is found that the approach, OpsiD, is capable of predicting the inhibition capacity of siRNA against a target mRNA with improved results over the state of the art techniques. Also we are able to understand the influence of whole stacking energy on efficiency of siRNA. The model is further improved by including the ability to identify the “off-target possibility” of predicted siRNA on non-target genes. Thus the proposed model, OpsiD, can predict optimized siRNA by considering both “inhibition efficiency on target genes and off-target possibility on non-target genes”, with improved inhibition efficiency, specificity and sensitivity. Since we have taken efforts to optimize the siRNA efficacy in terms of “inhibition efficiency and offtarget possibility”, we hope that the risk of “off-target effect” while doing gene silencing in various bioinformatics fields can be overcome to a great extent. These findings may provide new insights into cancer diagnosis, prognosis and therapy by gene silencing. The approach may be found useful for designing exogenous siRNA for therapeutic applications and gene silencing techniques in different areas of bioinformatics.

Análisis de la Comunicación no Verbal en el discurso de Jorge Eliécer Gaitán. Un acercamiento a las nuevas estrategias de comunicación política en Colombia. Período 1944 - 1948

Esta investigación busca demostrar cómo las estrategias comunicativas no verbales, empleadas por Gaitán, influyeron de manera positiva en su discurso político. Así, el dominio consciente e inconsciente de elementos no verbales funciona estratégicamente para complementar su discurso.

Prediction of global and local model quality in CASP8 using the ModFOLD server

The development of effective methods for predicting the quality of three-dimensional (3D) models is fundamentally important for the success of tertiary structure (TS) prediction strategies. Since CASP7, the Quality Assessment (QA) category has existed to gauge the ability of various model quality assessment programs (MQAPs) at predicting the relative quality of individual 3D models. For the CASP8 experiment, automated predictions were submitted in the QA category using two methods from the ModFOLD server-ModFOLD version 1.1 and ModFOLDclust. ModFOLD version 1.1 is a single-model machine learning based method, which was used for automated predictions of global model quality (QMODE1). ModFOLDclust is a simple clustering based method, which was used for automated predictions of both global and local quality (QMODE2). In addition, manual predictions of model quality were made using ModFOLD version 2.0-an experimental method that combines the scores from ModFOLDclust and ModFOLD v1.1. Predictions from the ModFOLDclust method were the most successful of the three in terms of the global model quality, whilst the ModFOLD v1.1 method was comparable in performance to other single-model based methods. In addition, the ModFOLDclust method performed well at predicting the per-residue, or local, model quality scores. Predictions of the per-residue errors in our own 3D models, selected using the ModFOLD v2.0 method, were also the most accurate compared with those from other methods. All of the MQAPs described are publicly accessible via the ModFOLD server at: http://www.reading.ac.uk/bioinf/ModFOLD/. The methods are also freely available to download from: http://www.reading.ac.uk/bioinf/downloads/.

Do children with Williams syndrome really have good vocabulary knowledge? Methods for comparing cognitive and linguistic abilities in developmental disorders

The comparison of cognitive and linguistic skills in individuals with developmental disorders is fraught with methodological and psychometric difficulties. In this paper, we illustrate some of these issues by comparing the receptive vocabulary knowledge and non-verbal reasoning abilities of 41 children with Williams syndrome, a genetic disorder in which language abilities are often claimed to be relatively strong. Data from this group were compared with data from typically developing children, children with Down syndrome, and children with non-specific learning difficulties using a number of approaches including comparison of age-equivalent scores, matching, analysis of covariance, and regression-based standardization. Across these analyses children with Williams syndrome consistently demonstrated relatively good receptive vocabulary knowledge, although this effect appeared strongest in the oldest children.

Increasing detection rate of user-to-root attacks using genetic algorithms

An extensive set of machine learning and pattern classification techniques trained and tested on KDD dataset failed in detecting most of the user-to-root attacks. This paper aims to provide an approach for mitigating negative aspects of the mentioned dataset, which led to low detection rates. Genetic algorithm is employed to implement rules for detecting various types of attacks. Rules are formed of the features of the dataset identified as the most important ones for each attack type. In this way we introduce high level of generality and thus achieve high detection rates, but also gain high reduction of the system training time. Thenceforth we re-check the decision of the user-to- root rules with the rules that detect other types of attacks. In this way we decrease the false-positive rate. The model was verified on KDD 99, demonstrating higher detection rates than those reported by the state- of-the-art while maintaining low false-positive rate.

Detection of mutations in Salmonella enterica gyrA, gyrB, parC and parE genes by denaturing high performance liquid chromatography (DHPLC) using standard HPLC instrumentation

Aims: Quinolone antibiotics are the agents of choice for treating systemic Salmonella infections. Resistance to quinolones is usually mediated by mutations in the DNA gyrase gene gyrA. Here we report the evaluation of standard HPLC equipment for the detection of mutations (single nucleotide polymorphisms; SNPs) in gyrA, gyrB, parC and parE by denaturing high performance liquid chromatography (DHPLC). Methods: A panel of Salmonella strains was assembled which comprised those with known different mutations in gyrA (n = 8) and fluoroquinolone-susceptible and -resistant strains (n = 50) that had not been tested for mutations in gyrA. Additionally, antibiotic-susceptible strains of serotypes other than Salmonella enterica serovar Typhimurium strains were examined for serotype-specific mutations in gyrB (n = 4), parC (n = 6) and parE (n = 1). Wild-type (WT) control DNA was prepared from Salmonella Typhimurium NCTC 74. The DNA of respective strains was amplified by PCR using Optimase (R) proofreading DNA polymerase. Duplex DNA samples were analysed using an Agilent A1100 HPLC system with a Varian Helix (TM) DNA column. Sequencing was used to validate mutations detected by DHPLC in the strains with unknown mutations. Results: Using this HPLC system, mutations in gyrA, gyrB, parC and parE were readily detected by comparison with control chromatograms. Sequencing confirmed the gyrA predicted mutations as detected by DHPLC in the unknown strains and also confirmed serotype-associated sequence changes in non-Typhimurium serotypes. Conclusions: The results demonstrated that a non-specialist standard HPLC machine fitted with a generally available column can be used to detect SNPs in gyrA, gyrB, parC and parE genes by DHPLC. Wider applications should be possible.

Second language influence on first language motion event encoding and categorization in Spanish-speaking children learning L2 English

Studies show cross-linguistic differences in motion event encoding, such that English speakers preferentially encode manner of motion more than Spanish speakers, who preferentially encode path of motion. Focusing on native Spanish speaking children (aged 5;00-9;00) learning L2 English, we studied path and manner verb preferences during descriptions of motion stimuli, and tested the linguistic relativity hypothesis by investigating categorization preferences in a non-verbal similarity judgement task of motion clip triads. Results revealed L2 influence on L1 motion event encoding, such that bilinguals used more manner verbs and fewer path verbs in their L1, under the influence of English. We found no effects of linguistic structure on non-verbal similarity judgements, and demonstrate for the first time effects of L2 on L1 lexicalization in child L2 learners in the domain of motion events. This pattern of verbal behaviour supports theories of bilingual semantic representation that postulate a merged lexico-semantic system in early bilinguals.

Building binary-tree-based multiclass classifiers using separability measures

Various popular machine learning techniques, like support vector machines, are originally conceived for the solution of two-class (binary) classification problems. However, a large number of real problems present more than two classes. A common approach to generalize binary learning techniques to solve problems with more than two classes, also known as multiclass classification problems, consists of hierarchically decomposing the multiclass problem into multiple binary sub-problems, whose outputs are combined to define the predicted class. This strategy results in a tree of binary classifiers, where each internal node corresponds to a binary classifier distinguishing two groups of classes and the leaf nodes correspond to the problem classes. This paper investigates how measures of the separability between classes can be employed in the construction of binary-tree-based multiclass classifiers, adapting the decompositions performed to each particular multiclass problem. (C) 2010 Elsevier B.V. All rights reserved.

A hybrid approach to learn with imbalanced classes using evolutionary algorithms

There is an increasing interest in the application of Evolutionary Algorithms (EAs) to induce classification rules. This hybrid approach can benefit areas where classical methods for rule induction have not been very successful. One example is the induction of classification rules in imbalanced domains. Imbalanced data occur when one or more classes heavily outnumber other classes. Frequently, classical machine learning (ML) classifiers are not able to learn in the presence of imbalanced data sets, inducing classification models that always predict the most numerous classes. In this work, we propose a novel hybrid approach to deal with this problem. We create several balanced data sets with all minority class cases and a random sample of majority class cases. These balanced data sets are fed to classical ML systems that produce rule sets. The rule sets are combined creating a pool of rules and an EA is used to build a classifier from this pool of rules. This hybrid approach has some advantages over undersampling, since it reduces the amount of discarded information, and some advantages over oversampling, since it avoids overfitting. The proposed approach was experimentally analysed and the experimental results show an improvement in the classification performance measured as the area under the receiver operating characteristics (ROC) curve.

Semantic mapping using mobile robots

Robotic mapping is the process of automatically constructing an environment representation using mobile robots. We address the problem of semantic mapping, which consists of using mobile robots to create maps that represent not only metric occupancy but also other properties of the environment. Specifically, we develop techniques to build maps that represent activity and navigability of the environment. Our approach to semantic mapping is to combine machine learning techniques with standard mapping algorithms. Supervised learning methods are used to automatically associate properties of space to the desired classification patterns. We present two methods, the first based on hidden Markov models and the second on support vector machines. Both approaches have been tested and experimentally validated in two problem domains: terrain mapping and activity-based mapping.

A Road Following Approach Using Artificial Neural Networks Combinations

Navigation is a broad topic that has been receiving considerable attention from the mobile robotic community over the years. In order to execute autonomous driving in outdoor urban environments it is necessary to identify parts of the terrain that can be traversed and parts that should be avoided. This paper describes an analyses of terrain identification based on different visual information using a MLP artificial neural network and combining responses of many classifiers. Experimental tests using a vehicle and a video camera have been conducted in real scenarios to evaluate the proposed approach.