Context-free and context-sensitive dynamics in recurrent neural networks

Continuous-valued recurrent neural networks can learn mechanisms for processing context-free languages. The dynamics of such networks is usually based on damped oscillation around fixed points in state space and requires that the dynamical components are arranged in certain ways. It is shown that qualitatively similar dynamics with similar constraints hold for a(n)b(n)c(n), a context-sensitive language. The additional difficulty with a(n)b(n)c(n), compared with the context-free language a(n)b(n), consists of 'counting up' and 'counting down' letters simultaneously. The network solution is to oscillate in two principal dimensions, one for counting up and one for counting down. This study focuses on the dynamics employed by the sequential cascaded network, in contrast to the simple recurrent network, and the use of backpropagation through time. Found solutions generalize well beyond training data, however, learning is not reliable. The contribution of this study lies in demonstrating how the dynamics in recurrent neural networks that process context-free languages can also be employed in processing some context-sensitive languages (traditionally thought of as requiring additional computation resources). This continuity of mechanism between language classes contributes to our understanding of neural networks in modelling language learning and processing.

On learning context-free and context-sensitive languages

The long short-term memory (LSTM) is not the only neural network which learns a context sensitive language. Second-order sequential cascaded networks (SCNs) are able to induce means from a finite fragment of a context-sensitive language for processing strings outside the training set. The dynamical behavior of the SCN is qualitatively distinct from that observed in LSTM networks. Differences in performance and dynamics are discussed.

An evaluation of active lecturing in a computer networks course

The article describes an attempt to improve student learning outcomes in a computer networks course by making lectures more active learning experiences. Quick quizzes, group and individual exercises, the review of student questions, as well as multiple breaks, were incorporated into the weekly three-hour lectures. Student responses to the modified lectures was overwhelmingly positive: over 85% of respondents agreed that the lectures aided understanding, with large majorities of the respondents finding the individual activities useful to their learning. Although student examination performance improved over the previous year, performance on an examination question that was designed to examine deep understanding remained unchanged.

Learning the dynamics of embedded clauses

Recent work by Siegelmann has shown that the computational power of recurrent neural networks matches that of Turing Machines. One important implication is that complex language classes (infinite languages with embedded clauses) can be represented in neural networks. Proofs are based on a fractal encoding of states to simulate the memory and operations of stacks. In the present work, it is shown that similar stack-like dynamics can be learned in recurrent neural networks from simple sequence prediction tasks. Two main types of network solutions are found and described qualitatively as dynamical systems: damped oscillation and entangled spiraling around fixed points. The potential and limitations of each solution type are established in terms of generalization on two different context-free languages. Both solution types constitute novel stack implementations - generally in line with Siegelmann's theoretical work - which supply insights into how embedded structures of languages can be handled in analog hardware.

Artificial neural networks for automatic modelling of the pectus excavatum corrective prosthesis

Pectus excavatum is the most common deformity of the thorax and usually comprises Computed Tomography (CT) examination for pre-operative diagnosis. Aiming at the elimination of the high amounts of CT radiation exposure, this work presents a new methodology for the replacement of CT by a laser scanner (radiation-free) in the treatment of pectus excavatum using personally modeled prosthesis. The complete elimination of CT involves the determination of ribs external outline, at the maximum sternum depression point for prosthesis placement, based on chest wall skin surface information, acquired by a laser scanner. The developed solution resorts to artificial neural networks trained with data vectors from 165 patients. Scaled Conjugate Gradient, Levenberg-Marquardt, Resilient Back propagation and One Step Secant gradient learning algorithms were used. The training procedure was performed using the soft tissue thicknesses, determined using image processing techniques that automatically segment the skin and rib cage. The developed solution was then used to determine the ribs outline in data from 20 patient scanners. Tests revealed that ribs position can be estimated with an average error of about 6.82±5.7 mm for the left and right side of the patient. Such an error range is well below current prosthesis manual modeling (11.7±4.01 mm) even without CT imagiology, indicating a considerable step forward towards CT replacement by a 3D scanner for prosthesis personalization.

Enhancing reflexivity and technology in translation learning: case study on the use of ePortfolio as a training environment

In this paper we describe a casestudy of an experiment on how reflexivity and technology can enhance learning, by using ePorfolios as a training environment to develop translation skills. Translation is today a multiskilled job and translators need to assure their clients a good performance and quality, both in language and in technology domains. In order to accomplish it, for the translator all the tasks and processes he develops appear as crucial, being pretranslation and posttranslation processes equally important as the translation itself, namely as far as autonomy, reflexive and critical skills are concerned. Finally, the need and relevance for collaborative tasks and networks amongst virtual translation communities, led us to the decision of implementing ePortfolios as a tool to develop the requested skills and extend the use of Internet in translation, namely in terminology management phases, for the completion of each task, by helping students in the management of the projects deadlines, improving their knowledge on the construction and management of translation resources and deepening their awareness about the concepts related to the development and usability of ePorfolios.

Estudo para a implementação de plataformas de e-learning no sistema de formação dos recursos humanos da saúde: o caso particular dos enfermeiros de um hospital privado

Mestrado em Intervenção Sócio-Organizacional na Saúde - Área de especialização: Políticas de Administração e Gestão de Serviços de Saúde.

Symbolic Knowledge Extraction from Trained Neural Networks Governed by Lukasiewicz Logics

This work describes a methodology to extract symbolic rules from trained neural networks. In our approach, patterns on the network are codified using formulas on a Lukasiewicz logic. For this we take advantage of the fact that every connective in this multi-valued logic can be evaluated by a neuron in an artificial network having, by activation function the identity truncated to zero and one. This fact simplifies symbolic rule extraction and allows the easy injection of formulas into a network architecture. We trained this type of neural network using a back-propagation algorithm based on Levenderg-Marquardt algorithm, where in each learning iteration, we restricted the knowledge dissemination in the network structure. This makes the descriptive power of produced neural networks similar to the descriptive power of Lukasiewicz logic language, minimizing the information loss on the translation between connectionist and symbolic structures. To avoid redundance on the generated network, the method simplifies them in a pruning phase, using the "Optimal Brain Surgeon" algorithm. We tested this method on the task of finding the formula used on the generation of a given truth table. For real data tests, we selected the Mushrooms data set, available on the UCI Machine Learning Repository.

Contextual intelligent load management with ANN adaptive learning module

With the current increase of energy resources prices and environmental concerns intelligent load management systems are gaining more and more importance. This paper concerns a SCADA House Intelligent Management (SHIM) system that includes an optimization module using deterministic and genetic algorithm approaches. SHIM undertakes contextual load management based on the characterization of each situation. SHIM considers available generation resources, load demand, supplier/market electricity price, and consumers’ constraints and preferences. The paper focus on the recently developed learning module which is based on artificial neural networks (ANN). The learning module allows the adjustment of users’ profiles along SHIM lifetime. A case study considering a system with fourteen discrete and four variable loads managed by a SHIM system during five consecutive similar weekends is presented.

FMRI 3D registration based on Fourier space subsets using neural networks

In this work, we present a neural network (NN) based method designed for 3D rigid-body registration of FMRI time series, which relies on a limited number of Fourier coefficients of the images to be aligned. These coefficients, which are comprised in a small cubic neighborhood located at the first octant of a 3D Fourier space (including the DC component), are then fed into six NN during the learning stage. Each NN yields the estimates of a registration parameter. The proposed method was assessed for 3D rigid-body transformations, using DC neighborhoods of different sizes. The mean absolute registration errors are of approximately 0.030 mm in translations and 0.030 deg in rotations, for the typical motion amplitudes encountered in FMRI studies. The construction of the training set and the learning stage are fast requiring, respectively, 90 s and 1 to 12 s, depending on the number of input and hidden units of the NN. We believe that NN-based approaches to the problem of FMRI registration can be of great interest in the future. For instance, NN relying on limited K-space data (possibly in navigation echoes) can be a valid solution to the problem of prospective (in frame) FMRI registration.

Facebook vs moodle : Surveying university students on the use of learning management systems to support learning activities outside the classroom

CISTI'2015 - 10ª Conferência Ibérica de Sistemas e Tecnologias de Informação, 17 a 20 de junho de 2015, Águeda, Aveiro, Portugal.

Ensemble: an e-learning framework

E-Learning frameworks are conceptual tools to organize networks of elearning services. Most frameworks cover areas that go beyond the scope of e-learning, from course to financial management, and neglects the typical activities in everyday life of teachers and students at schools such as the creation, delivery, resolution and evaluation of assignments. This paper presents the Ensemble framework - an e-learning framework exclusively focused on the teaching-learning process through the coordination of pedagogical services. The framework presents an abstract data, integration and evaluation model based on content and communications specifications. These specifications must base the implementation of networks in specialized domains with complex evaluations. In this paper we specialize the framework for two domains with complex evaluation: computer programming and computer-aided design (CAD). For each domain we highlight two Ensemble hotspots: data and evaluations procedures. In the former we formally describe the exercise and present possible extensions. In the latter, we describe the automatic evaluation procedures.

Orchestration of e-learning services for automatic evaluation of programming exercises

Managing programming exercises require several heterogeneous systems such as evaluation engines, learning objects repositories and exercise resolution environments. The coordination of networks of such disparate systems is rather complex. These tools would be too specific to incorporate in an e-Learning platform. Even if they could be provided as pluggable components, the burden of maintaining them would be prohibitive to institutions with few courses in those domains. This work presents a standard based approach for the coordination of a network of e-Learning systems participating on the automatic evaluation of programming exercises. The proposed approach uses a pivot component to orchestrate the interaction among all the systems using communication standards. This approach was validated through its effective use on classroom and we present some preliminary results.

Data gathering approach in dense sensor networks

Sensor/actuator networks promised to extend automated monitoring and control into industrial processes. Avionic system is one of the prominent technologies that can highly gain from dense sensor/actuator deployments. An aircraft with smart sensing skin would fulfill the vision of affordability and environmental friendliness properties by reducing the fuel consumption. Achieving these properties is possible by providing an approximate representation of the air flow across the body of the aircraft and suppressing the detected aerodynamic drags. To the best of our knowledge, getting an accurate representation of the physical entity is one of the most significant challenges that still exists with dense sensor/actuator network. This paper offers an efficient way to acquire sensor readings from very large sensor/actuator network that are located in a small area (dense network). It presents LIA algorithm, a Linear Interpolation Algorithm that provides two important contributions. First, it demonstrates the effectiveness of employing a transformation matrix to mimic the environmental behavior. Second, it renders a smart solution for updating the previously defined matrix through a procedure called learning phase. Simulation results reveal that the average relative error in LIA algorithm can be reduced by as much as 60% by exploiting transformation matrix.

Automatic learning for the classification of chemical reactions and in statistical thermodynamics

This Thesis describes the application of automatic learning methods for a) the classification of organic and metabolic reactions, and b) the mapping of Potential Energy Surfaces(PES). The classification of reactions was approached with two distinct methodologies: a representation of chemical reactions based on NMR data, and a representation of chemical reactions from the reaction equation based on the physico-chemical and topological features of chemical bonds. NMR-based classification of photochemical and enzymatic reactions. Photochemical and metabolic reactions were classified by Kohonen Self-Organizing Maps (Kohonen SOMs) and Random Forests (RFs) taking as input the difference between the 1H NMR spectra of the products and the reactants. The development of such a representation can be applied in automatic analysis of changes in the 1H NMR spectrum of a mixture and their interpretation in terms of the chemical reactions taking place. Examples of possible applications are the monitoring of reaction processes, evaluation of the stability of chemicals, or even the interpretation of metabonomic data. A Kohonen SOM trained with a data set of metabolic reactions catalysed by transferases was able to correctly classify 75% of an independent test set in terms of the EC number subclass. Random Forests improved the correct predictions to 79%. With photochemical reactions classified into 7 groups, an independent test set was classified with 86-93% accuracy. The data set of photochemical reactions was also used to simulate mixtures with two reactions occurring simultaneously. Kohonen SOMs and Feed-Forward Neural Networks (FFNNs) were trained to classify the reactions occurring in a mixture based on the 1H NMR spectra of the products and reactants. Kohonen SOMs allowed the correct assignment of 53-63% of the mixtures (in a test set). Counter-Propagation Neural Networks (CPNNs) gave origin to similar results. The use of supervised learning techniques allowed an improvement in the results. They were improved to 77% of correct assignments when an ensemble of ten FFNNs were used and to 80% when Random Forests were used. This study was performed with NMR data simulated from the molecular structure by the SPINUS program. In the design of one test set, simulated data was combined with experimental data. The results support the proposal of linking databases of chemical reactions to experimental or simulated NMR data for automatic classification of reactions and mixtures of reactions. Genome-scale classification of enzymatic reactions from their reaction equation. The MOLMAP descriptor relies on a Kohonen SOM that defines types of bonds on the basis of their physico-chemical and topological properties. The MOLMAP descriptor of a molecule represents the types of bonds available in that molecule. The MOLMAP descriptor of a reaction is defined as the difference between the MOLMAPs of the products and the reactants, and numerically encodes the pattern of bonds that are broken, changed, and made during a chemical reaction. The automatic perception of chemical similarities between metabolic reactions is required for a variety of applications ranging from the computer validation of classification systems, genome-scale reconstruction (or comparison) of metabolic pathways, to the classification of enzymatic mechanisms. Catalytic functions of proteins are generally described by the EC numbers that are simultaneously employed as identifiers of reactions, enzymes, and enzyme genes, thus linking metabolic and genomic information. Different methods should be available to automatically compare metabolic reactions and for the automatic assignment of EC numbers to reactions still not officially classified. In this study, the genome-scale data set of enzymatic reactions available in the KEGG database was encoded by the MOLMAP descriptors, and was submitted to Kohonen SOMs to compare the resulting map with the official EC number classification, to explore the possibility of predicting EC numbers from the reaction equation, and to assess the internal consistency of the EC classification at the class level. A general agreement with the EC classification was observed, i.e. a relationship between the similarity of MOLMAPs and the similarity of EC numbers. At the same time, MOLMAPs were able to discriminate between EC sub-subclasses. EC numbers could be assigned at the class, subclass, and sub-subclass levels with accuracies up to 92%, 80%, and 70% for independent test sets. The correspondence between chemical similarity of metabolic reactions and their MOLMAP descriptors was applied to the identification of a number of reactions mapped into the same neuron but belonging to different EC classes, which demonstrated the ability of the MOLMAP/SOM approach to verify the internal consistency of classifications in databases of metabolic reactions. RFs were also used to assign the four levels of the EC hierarchy from the reaction equation. EC numbers were correctly assigned in 95%, 90%, 85% and 86% of the cases (for independent test sets) at the class, subclass, sub-subclass and full EC number level,respectively. Experiments for the classification of reactions from the main reactants and products were performed with RFs - EC numbers were assigned at the class, subclass and sub-subclass level with accuracies of 78%, 74% and 63%, respectively. In the course of the experiments with metabolic reactions we suggested that the MOLMAP / SOM concept could be extended to the representation of other levels of metabolic information such as metabolic pathways. Following the MOLMAP idea, the pattern of neurons activated by the reactions of a metabolic pathway is a representation of the reactions involved in that pathway - a descriptor of the metabolic pathway. This reasoning enabled the comparison of different pathways, the automatic classification of pathways, and a classification of organisms based on their biochemical machinery. The three levels of classification (from bonds to metabolic pathways) allowed to map and perceive chemical similarities between metabolic pathways even for pathways of different types of metabolism and pathways that do not share similarities in terms of EC numbers. Mapping of PES by neural networks (NNs). In a first series of experiments, ensembles of Feed-Forward NNs (EnsFFNNs) and Associative Neural Networks (ASNNs) were trained to reproduce PES represented by the Lennard-Jones (LJ) analytical potential function. The accuracy of the method was assessed by comparing the results of molecular dynamics simulations (thermal, structural, and dynamic properties) obtained from the NNs-PES and from the LJ function. The results indicated that for LJ-type potentials, NNs can be trained to generate accurate PES to be used in molecular simulations. EnsFFNNs and ASNNs gave better results than single FFNNs. A remarkable ability of the NNs models to interpolate between distant curves and accurately reproduce potentials to be used in molecular simulations is shown. The purpose of the first study was to systematically analyse the accuracy of different NNs. Our main motivation, however, is reflected in the next study: the mapping of multidimensional PES by NNs to simulate, by Molecular Dynamics or Monte Carlo, the adsorption and self-assembly of solvated organic molecules on noble-metal electrodes. Indeed, for such complex and heterogeneous systems the development of suitable analytical functions that fit quantum mechanical interaction energies is a non-trivial or even impossible task. The data consisted of energy values, from Density Functional Theory (DFT) calculations, at different distances, for several molecular orientations and three electrode adsorption sites. The results indicate that NNs require a data set large enough to cover well the diversity of possible interaction sites, distances, and orientations. NNs trained with such data sets can perform equally well or even better than analytical functions. Therefore, they can be used in molecular simulations, particularly for the ethanol/Au (111) interface which is the case studied in the present Thesis. Once properly trained, the networks are able to produce, as output, any required number of energy points for accurate interpolations.