Designing Regularizers and Architectures for Recurrent Neural Networks

Cette thèse contribue a la recherche vers l'intelligence artificielle en utilisant des méthodes connexionnistes. Les réseaux de neurones récurrents sont un ensemble de modèles séquentiels de plus en plus populaires capable en principe d'apprendre des algorithmes arbitraires. Ces modèles effectuent un apprentissage en profondeur, un type d'apprentissage machine. Sa généralité et son succès empirique en font un sujet intéressant pour la recherche et un outil prometteur pour la création de l'intelligence artificielle plus générale. Le premier chapitre de cette thèse donne un bref aperçu des sujets de fonds: l'intelligence artificielle, l'apprentissage machine, l'apprentissage en profondeur et les réseaux de neurones récurrents. Les trois chapitres suivants couvrent ces sujets de manière de plus en plus spécifiques. Enfin, nous présentons quelques contributions apportées aux réseaux de neurones récurrents. Le chapitre \ref{arxiv1} présente nos travaux de régularisation des réseaux de neurones récurrents. La régularisation vise à améliorer la capacité de généralisation du modèle, et joue un role clé dans la performance de plusieurs applications des réseaux de neurones récurrents, en particulier en reconnaissance vocale. Notre approche donne l'état de l'art sur TIMIT, un benchmark standard pour cette tâche. Le chapitre \ref{cpgp} présente une seconde ligne de travail, toujours en cours, qui explore une nouvelle architecture pour les réseaux de neurones récurrents. Les réseaux de neurones récurrents maintiennent un état caché qui représente leurs observations antérieures. L'idée de ce travail est de coder certaines dynamiques abstraites dans l'état caché, donnant au réseau une manière naturelle d'encoder des tendances cohérentes de l'état de son environnement. Notre travail est fondé sur un modèle existant; nous décrivons ce travail et nos contributions avec notamment une expérience préliminaire.

Introduction to Special issue on the Symposium on the Application of Neural Networks to the Earth Sciences

Papers in this issue of Natural Resources Research are from the “Symposium on the Application of Neural Networks to the Earth Sciences,” held 20–21 August 2002 at NASA Moffet Field, Mountain View, California. The Symposium represents the Seventh International Symposium on Mineral Exploration (ISME-02). It was sponsored by the Mining and Materials Processing Institute of Japan (MMIJ), the US Geological Survey, the Circum-Pacific Council, and NASA. The ISME symposia have been held every two years in order to bring together scientists actively working on diverse quantitative methods applied to the earth sciences. Although the title, International Symposium on Mineral Exploration, suggests exclusive focus on mineral exploration, interests and presentations always have been wide-ranging—talks presented at this symposium are no exception.

GANN: Genetic algorithm neural networks for the detection of conserved combinations of features in DNA

Background: The multitude of motif detection algorithms developed to date have largely focused on the detection of patterns in primary sequence. Since sequence-dependent DNA structure and flexibility may also play a role in protein-DNA interactions, the simultaneous exploration of sequence-and structure-based hypotheses about the composition of binding sites and the ordering of features in a regulatory region should be considered as well. The consideration of structural features requires the development of new detection tools that can deal with data types other than primary sequence. Results: GANN ( available at http://bioinformatics.org.au/gann) is a machine learning tool for the detection of conserved features in DNA. The software suite contains programs to extract different regions of genomic DNA from flat files and convert these sequences to indices that reflect sequence and structural composition or the presence of specific protein binding sites. The machine learning component allows the classification of different types of sequences based on subsamples of these indices, and can identify the best combinations of indices and machine learning architecture for sequence discrimination. Another key feature of GANN is the replicated splitting of data into training and test sets, and the implementation of negative controls. In validation experiments, GANN successfully merged important sequence and structural features to yield good predictive models for synthetic and real regulatory regions. Conclusion: GANN is a flexible tool that can search through large sets of sequence and structural feature combinations to identify those that best characterize a set of sequences.

The applicability of recurrent neural networks for biological sequence analysis

Selection of machine learning techniques requires a certain sensitivity to the requirements of the problem. In particular, the problem can be made more tractable by deliberately using algorithms that are biased toward solutions of the requisite kind. In this paper, we argue that recurrent neural networks have a natural bias toward a problem domain of which biological sequence analysis tasks are a subset. We use experiments with synthetic data to illustrate this bias. We then demonstrate that this bias can be exploitable using a data set of protein sequences containing several classes of subcellular localization targeting peptides. The results show that, compared with feed forward, recurrent neural networks will generally perform better on sequence analysis tasks. Furthermore, as the patterns within the sequence become more ambiguous, the choice of specific recurrent architecture becomes more critical.

Tracking the states of a nonlinear and nonstationary system in the weight-space of artificial neural networks

We propose a novel interpretation and usage of Neural Network (NN) in modeling physiological signals, which are allowed to be nonlinear and/or nonstationary. The method consists of training a NN for the k-step prediction of a physiological signal, and then examining the connection-weight-space (CWS) of the NN to extract information about the signal generator mechanism. We de. ne a novel feature, Normalized Vector Separation (gamma(ij)), to measure the separation of two arbitrary states i and j in the CWS and use it to track the state changes of the generating system. The performance of the method is examined via synthetic signals and clinical EEG. Synthetic data indicates that gamma(ij) can track the system down to a SNR of 3.5 dB. Clinical data obtained from three patients undergoing carotid endarterectomy of the brain showed that EEG could be modeled (within a root-means-squared-error of 0.01) by the proposed method, and the blood perfusion state of the brain could be monitored via gamma(ij), with small NNs having no more than 21 connection weight altogether.

Detecting and sorting targeting peptides wtih neural networks and support vector machines

This paper presents a composite multi-layer classifier system for predicting the subcellular localization of proteins based on their amino acid sequence. The work is an extension of our previous predictor PProwler v1.1 which is itself built upon the series of predictors SignalP and TargetP. In this study we outline experiments conducted to improve the classifier design. The major improvement came from using Support Vector machines as a "smart gate" sorting the outputs of several different targeting peptide detection networks. Our final model (PProwler v1.2) gives MCC values of 0.873 for non-plant and 0.849 for plant proteins. The model improves upon the accuracy of our previous subcellular localization predictor (PProwler v1.1) by 2% for plant data (which represents 7.5% improvement upon TargetP).