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.

Reinforcement Learning Approaches to Power System Scheduling

One major component of power system operation is generation scheduling. The objective of the work is to develop efficient control strategies to the power scheduling problems through Reinforcement Learning approaches. The three important active power scheduling problems are Unit Commitment, Economic Dispatch and Automatic Generation Control. Numerical solution methods proposed for solution of power scheduling are insufficient in handling large and complex systems. Soft Computing methods like Simulated Annealing, Evolutionary Programming etc., are efficient in handling complex cost functions, but find limitation in handling stochastic data existing in a practical system. Also the learning steps are to be repeated for each load demand which increases the computation time.Reinforcement Learning (RL) is a method of learning through interactions with environment. The main advantage of this approach is it does not require a precise mathematical formulation. It can learn either by interacting with the environment or interacting with a simulation model. Several optimization and control problems have been solved through Reinforcement Learning approach. The application of Reinforcement Learning in the field of Power system has been a few. The objective is to introduce and extend Reinforcement Learning approaches for the active power scheduling problems in an implementable manner. The main objectives can be enumerated as:(i) Evolve Reinforcement Learning based solutions to the Unit Commitment Problem.(ii) Find suitable solution strategies through Reinforcement Learning approach for Economic Dispatch. (iii) Extend the Reinforcement Learning solution to Automatic Generation Control with a different perspective. (iv) Check the suitability of the scheduling solutions to one of the existing power systems.First part of the thesis is concerned with the Reinforcement Learning approach to Unit Commitment problem. Unit Commitment Problem is formulated as a multi stage decision process. Q learning solution is developed to obtain the optimwn commitment schedule. Method of state aggregation is used to formulate an efficient solution considering the minimwn up time I down time constraints. The performance of the algorithms are evaluated for different systems and compared with other stochastic methods like Genetic Algorithm.Second stage of the work is concerned with solving Economic Dispatch problem. A simple and straight forward decision making strategy is first proposed in the Learning Automata algorithm. Then to solve the scheduling task of systems with large number of generating units, the problem is formulated as a multi stage decision making task. The solution obtained is extended in order to incorporate the transmission losses in the system. To make the Reinforcement Learning solution more efficient and to handle continuous state space, a fimction approximation strategy is proposed. The performance of the developed algorithms are tested for several standard test cases. Proposed method is compared with other recent methods like Partition Approach Algorithm, Simulated Annealing etc.As the final step of implementing the active power control loops in power system, Automatic Generation Control is also taken into consideration.Reinforcement Learning has already been applied to solve Automatic Generation Control loop. The RL solution is extended to take up the approach of common frequency for all the interconnected areas, more similar to practical systems. Performance of the RL controller is also compared with that of the conventional integral controller.In order to prove the suitability of the proposed methods to practical systems, second plant ofNeyveli Thennal Power Station (NTPS IT) is taken for case study. The perfonnance of the Reinforcement Learning solution is found to be better than the other existing methods, which provide the promising step towards RL based control schemes for practical power industry.Reinforcement Learning is applied to solve the scheduling problems in the power industry and found to give satisfactory perfonnance. Proposed solution provides a scope for getting more profit as the economic schedule is obtained instantaneously. Since Reinforcement Learning method can take the stochastic cost data obtained time to time from a plant, it gives an implementable method. As a further step, with suitable methods to interface with on line data, economic scheduling can be achieved instantaneously in a generation control center. Also power scheduling of systems with different sources such as hydro, thermal etc. can be looked into and Reinforcement Learning solutions can be achieved.

Performance Improvement of Fuzzy and Neuro Fuzzy Systems: Prediction of Learning Disabilities in School-age Children

Learning Disability (LD) is a classification including several disorders in which a child has difficulty in learning in a typical manner, usually caused by an unknown factor or factors. LD affects about 15% of children enrolled in schools. The prediction of learning disability is a complicated task since the identification of LD from diverse features or signs is a complicated problem. There is no cure for learning disabilities and they are life-long. The problems of children with specific learning disabilities have been a cause of concern to parents and teachers for some time. The aim of this paper is to develop a new algorithm for imputing missing values and to determine the significance of the missing value imputation method and dimensionality reduction method in the performance of fuzzy and neuro fuzzy classifiers with specific emphasis on prediction of learning disabilities in school age children. In the basic assessment method for prediction of LD, checklists are generally used and the data cases thus collected fully depends on the mood of children and may have also contain redundant as well as missing values. Therefore, in this study, we are proposing a new algorithm, viz. the correlation based new algorithm for imputing the missing values and Principal Component Analysis (PCA) for reducing the irrelevant attributes. After the study, it is found that, the preprocessing methods applied by us improves the quality of data and thereby increases the accuracy of the classifiers. The system is implemented in Math works Software Mat Lab 7.10. The results obtained from this study have illustrated that the developed missing value imputation method is very good contribution in prediction system and is capable of improving the performance of a classifier.

A Reinforcement Learning Algorithm to Economic Dispatch Considering Transmission Losses

Reinforcement Learning (RL) refers to a class of learning algorithms in which learning system learns which action to take in different situations by using a scalar evaluation received from the environment on performing an action. RL has been successfully applied to many multi stage decision making problem (MDP) where in each stage the learning systems decides which action has to be taken. Economic Dispatch (ED) problem is an important scheduling problem in power systems, which decides the amount of generation to be allocated to each generating unit so that the total cost of generation is minimized without violating system constraints. In this paper we formulate economic dispatch problem as a multi stage decision making problem. In this paper, we also develop RL based algorithm to solve the ED problem. The performance of our algorithm is compared with other recent methods. The main advantage of our method is it can learn the schedule for all possible demands simultaneously.

A Reinforcement Learning Approach to Economic Dispatch using Neural Networks

This paper presents a Reinforcement Learning (RL) approach to economic dispatch (ED) using Radial Basis Function neural network. We formulate the ED as an N stage decision making problem. We propose a novel architecture to store Qvalues and present a learning algorithm to learn the weights of the neural network. Even though many stochastic search techniques like simulated annealing, genetic algorithm and evolutionary programming have been applied to ED, they require searching for the optimal solution for each load demand. Also they find limitation in handling stochastic cost functions. In our approach once we learn the Q-values, we can find the dispatch for any load demand. We have recently proposed a RL approach to ED. In that approach, we could find only the optimum dispatch for a set of specified discrete values of power demand. The performance of the proposed algorithm is validated by taking IEEE 6 bus system, considering transmission losses

Identification of Problem-based learning components and their effects on graduates' competencies

This study investigated the relationship between higher education and the requirement of the world of work with an emphasis on the effect of problem-based learning (PBL) on graduates' competencies. The implementation of full PBL method is costly (Albanese & Mitchell, 1993; Berkson, 1993; Finucane, Shannon, & McGrath, 2009). However, the implementation of PBL in a less than curriculum-wide mode is more achievable in a broader context (Albanese, 2000). This means higher education institutions implement only a few PBL components in the curriculum. Or a teacher implements a few PBL components at the courses level. For this kind of implementation there is a need to identify PBL components and their effects on particular educational outputs (Hmelo-Silver, 2004; Newman, 2003). So far, however there has been little research about this topic. The main aims of this study were: (1) to identify each of PBL components which were manifested in the development of a valid and reliable PBL implementation questionnaire and (2) to determine the effect of each identified PBL component to specific graduates' competencies. The analysis was based on quantitative data collected in the survey of medicine graduates of Gadjah Mada University, Indonesia. A total of 225 graduates responded to the survey. The result of confirmatory factor analysis (CFA) showed that all individual constructs of PBL and graduates' competencies had acceptable GOFs (Goodness-of-fit). Additionally, the values of the factor loadings (standardize loading estimates), the AVEs (average variance extracted), CRs (construct reliability), and ASVs (average shared squared variance) showed the proof of convergent and discriminant validity. All values indicated valid and reliable measurements. The investigation of the effects of PBL showed that each PBL component had specific effects on graduates' competencies. Interpersonal competencies were affected by Student-centred learning (β = .137; p < .05) and Small group components (β = .078; p < .05). Problem as stimulus affected Leadership (β = .182; p < .01). Real-world problems affected Personal and organisational competencies (β = .140; p < .01) and Interpersonal competencies (β = .114; p < .05). Teacher as facilitator affected Leadership (β = 142; p < .05). Self-directed learning affected Field-related competencies (β = .080; p < .05). These results can help higher education institution and educator to have informed choice about the implementation of PBL components. With this information higher education institutions and educators could fulfil their educational goals and in the same time meet their limited resources. This study seeks to improve prior studies' research method in four major ways: (1) by indentifying PBL components based on theory and empirical data; (2) by using latent variables in the structural equation modelling instead of using a variable as a proxy of a construct; (3) by using CFA to validate the latent structure of the measurement, thus providing better evidence of validity; and (4) by using graduate survey data which is suitable for analysing PBL effects in the frame work of the relationship between higher education and the world of work.

Learning from Ambiguity

There are many learning problems for which the examples given by the teacher are ambiguously labeled. In this thesis, we will examine one framework of learning from ambiguous examples known as Multiple-Instance learning. Each example is a bag, consisting of any number of instances. A bag is labeled negative if all instances in it are negative. A bag is labeled positive if at least one instance in it is positive. Because the instances themselves are not labeled, each positive bag is an ambiguous example. We would like to learn a concept which will correctly classify unseen bags. We have developed a measure called Diverse Density and algorithms for learning from multiple-instance examples. We have applied these techniques to problems in drug design, stock prediction, and image database retrieval. These serve as examples of how to translate the ambiguity in the application domain into bags, as well as successful examples of applying Diverse Density techniques.

A Reinforcement-Learning Approach to Power Management

We describe an adaptive, mid-level approach to the wireless device power management problem. Our approach is based on reinforcement learning, a machine learning framework for autonomous agents. We describe how our framework can be applied to the power management problem in both infrastructure and ad~hoc wireless networks. From this thesis we conclude that mid-level power management policies can outperform low-level policies and are more convenient to implement than high-level policies. We also conclude that power management policies need to adapt to the user and network, and that a mid-level power management framework based on reinforcement learning fulfills these requirements.

Gestión de la actividad no presencial y autoevaluación de competencias = Management of student learning outside the classroom and the self-evaluation of competences

La asignatura troncal “Evaluación Psicológica” de los estudios de Psicología y del estudio de grado “Desarrollo humano en la sociedad de la información” de la Universidad de Girona consta de 12 créditos según la Ley Orgánica de Universidades. Hasta el año académico 2004-05 el trabajo no presencial del alumno consistía en la realización de una evaluación psicológica que se entregaba por escrito a final de curso y de la cual el estudiante obtenía una calificación y revisión si se solicitaba. En el camino hacia el Espacio Europeo de Educación Superior, esta asignatura consta de 9 créditos que equivalen a un total de 255 horas de trabajo presencial y no presencial del estudiante. En los años académicos 2005-06 y 2006-07 se ha creado una guía de trabajo para la gestión de la actividad no presencial con el objetivo de alcanzar aprendizajes a nivel de aplicación y solución de problemas/pensamiento crítico (Bloom, 1975) siguiendo las recomendaciones de la Agencia para la Calidad del Sistema Universitario de Cataluña (2005). La guía incorpora: los objetivos de aprendizaje, los criterios de evaluación, la descripción de las actividades, el cronograma semanal de trabajos para todo el curso, la especificación de las tutorías programadas para la revisión de los diversos pasos del proceso de evaluación psicológica y el uso del foro para el conocimiento, análisis y crítica constructiva de las evaluaciones realizadas por los compañeros

Learning and adaptation in physical heterogeneous teams of robots

In this paper we present a novel approach to assigning roles to robots in a team of physical heterogeneous robots. Its members compete for these roles and get rewards for them. The rewards are used to determine each agent’s preferences and which agents are better adapted to the environment. These aspects are included in the decision making process. Agent interactions are modelled using the concept of an ecosystem in which each robot is a species, resulting in emergent behaviour of the whole set of agents. One of the most important features of this approach is its high adaptability. Unlike some other learning techniques, this approach does not need to start a whole exploitation process when the environment changes. All this is exemplified by means of experiments run on a simulator. In addition, the algorithm developed was applied as applied to several teams of robots in order to analyse the impact of heterogeneity in these systems

Actitudes de los directivos en torno a la adopción del e-learning como herramienta de trabajo en las empresas

El desarrollo del presente documento constituye una investigación sobre las actitudes de los directivos frente a la adopción del e-learning como herramienta de trabajo en las organizaciones de Bogotá. Para ello se realizó una encuesta a 101 directivos, tomando como base el tipo de muestreo de conveniencia; esto con el objetivo de identificar sus actitudes frente al uso del e-learning y su influencia dentro de la organización. Como resultado se obtuvo que las actitudes de los directivos influencian en el uso de herramientas e-learning, así como también en las acciones que promueven su uso y en las actitudes de los empleados; por otro lado se identificó que las creencias relacionadas con la apropiación de herramientas e-learning y los factores facilitadores del uso de estas, influencian en las actitudes de los directivos. Lo anterior, corresponde a los análisis llevados a cabo a partir de los resultados contrastados con los estudios empíricos hallados y el marco teórico desarrollado.

Impact on the quality of learning as a result of the use of computers in schools

The educational software and computer assisted learning has been used in schools to promote the interest of students in new ways of thinking and learning so it can be useful in the reading learning process. Experimental studies performed in preschool and school age population have shown a better yield and a positive effect in reading, mathematics and cognitive skills in children who use educative software for fi fteen to twenty minutes a day periods. The goal of this study was to evaluate the progression in verbal, visual-motor integration and reading skills in children who were using educational software to compare them with a group in traditional pedagogic methodology. Results: All children were evaluated before using any kind of pedagogic approach. Initial evaluation revealed a lower–age score in all applied test. 11% of them were at high risk for learning disorders. There was a second evaluation that showed a significant positive change compared with the fi rst one. Nevertheless, despite some items, there were no general differences comparing the groups according if they were using or not a computer. In conclusion, policies on using educational software and computers must be revaluated due to the fact that children in our public schools come from a deprived environment with a lack of opportunities to use technologies.

The instrumentality of the portfolios in the teach-learning process: study with higher education Portuguese teachers

In a time when higher education come for deep changes and if intends an education more centered in the pupil, the teach-learning portfolios appears as a tool to use, because versatile and with innumerable potentialities. This article reveals the results gotten with higher education teachers, who we looked for to know if these appeal in use the teach-learning portfolios, in the curricular units that teach. We looked for, equally, to perceive of that forms these are used. This is an exploratory study, basically descriptive, that does not have pretensions to generalize for all the teaching population. We elaborated and we applied a questionnaire, with 290 teachers of higher education public, university and polytechnic. We verify that the percentage of the teachers that uses the portfolios in the teach- learning process is not very raised.

Continuous improvement programs as processes for organizational learning: a case study of a company in the food products industry

This article intends to show the relationships between quality practices and the process of organizational learning. When we look at the literature about programs of continuous improvement we see that theoreticians consider that the process of organizational learning is a superior stage in the quality culture adopted by companies. To investigate this possibility, we put together a series of indicators taken from classic authors who have written about organizational learning. Adopting a multiple methodology, we applied these indicators to two plants belonging to the Nestlé food product company which have introduced continuous improvement programs over the last two years.

Percepción de residentes de medicina de urgencias en Colombia del ambiente educativo en los servicios de urgencias

Introducción: La atención de calidad en urgencias sólo es posible si los médicos han recibido una enseñanza de alta calidad. La escala PHEEM (Postgraduate Hospital Educational Environment Measure) es un instrumento válido y fiable, utilizado internacionalmente para medir el entorno educativo, en la formación médica de posgrado. Materiales y métodos: Estudio de corte trasversal que utilizó la escala PHEEM versión en español para conocer el entorno educativo de los programas de urgencias. El coeficiente alfa de Cronbach se calculó para determinar la consistencia interna. Se aplicó estadística descriptiva a nivel global, por categorías e ítems de la escala PHEEM y se compararon resultados por sexo, año de residencia y programa. Resultados: 94 (94%) residentes llenaron el cuestionario. La puntuación media de la escala PHEEM fue 93,91 ± 23,71 (58,1% de la puntuación máxima) que se considera un ambiente educativo más positivo que negativo, pero con margen de mejora. Hubo una diferencia estadísticamente significativa en la percepción del ambiente educativo entre los programas de residencia (p =0,01). El instrumento es altamente confiable (alfa de Cronbach = 0,952). La barrera más frecuente en la enseñanza fue el hacinamiento y la evaluación fue percibida con el propósito de cumplir normas. Discusión: Los resultados de este estudio aportaron evidencia sobre la validez interna de la escala PHEEM en el contexto colombiano. Este estudio demostró cómo la medición del ambiente educativo en una especialidad médico-quirúrgica, con el uso de una herramienta cuantitativa, puede proporcionar información en relación a las fortalezas y debilidades de los programas.