Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Learning by the Dendritic Prediction of Somatic Spiking

Recent modeling of spike-timing-dependent plasticity indicates that plasticity involves as a third factor a local dendritic potential, besides pre- and postsynaptic firing times. We present a simple compartmental neuron model together with a non-Hebbian, biologically plausible learning rule for dendritic synapses where plasticity is modulated by these three factors. In functional terms, the rule seeks to minimize discrepancies between somatic firings and a local dendritic potential. Such prediction errors can arise in our model from stochastic fluctuations as well as from synaptic input, which directly targets the soma. Depending on the nature of this direct input, our plasticity rule subserves supervised or unsupervised learning. When a reward signal modulates the learning rate, reinforcement learning results. Hence a single plasticity rule supports diverse learning paradigms.

An innovative blended learning approach using virtual patients as preparation for skills laboratory training: perceptions of students and tutors

BACKGROUND Currently only a few reports exist on how to prepare medical students for skills laboratory training. We investigated how students and tutors perceive a blended learning approach using virtual patients (VPs) as preparation for skills training. METHODS Fifth-year medical students (N=617) were invited to voluntarily participate in a paediatric skills laboratory with four specially designed VPs as preparation. The cases focused on procedures in the laboratory using interactive questions, static and interactive images, and video clips. All students were asked to assess the VP design. After participating in the skills laboratory 310 of the 617 students were additionally asked to assess the blended learning approach through established questionnaires. Tutors' perceptions (N=9) were assessed by semi-structured interviews. RESULTS From the 617 students 1,459 VP design questionnaires were returned (59.1%). Of the 310 students 213 chose to participate in the skills laboratory; 179 blended learning questionnaires were returned (84.0%). Students provided high overall acceptance ratings of the VP design and blended learning approach. By using VPs as preparation, skills laboratory time was felt to be used more effectively. Tutors perceived students as being well prepared for the skills laboratory with efficient uses of time. CONCLUSION The overall acceptance of the blended learning approach was high among students and tutors. VPs proved to be a convenient cognitive preparation tool for skills training.

Forget about theory - practice is all? - Student teachers' learning in practicum

In 1999, all student teachers at secondary I level at the University of Bern who had to undertake an internship were asked to participate in a study on learning processes during practicum: 150 students and their mentors in three types of practicum participated—introductory practicum (after the first half‐year of studies), intermediate practicum (after two years of studies) and final practicum (after three years of studies). At the end of the practicum, student teachers and mentors completed questionnaires on preparing, teaching and post‐processing lessons. All student teachers, additionally, rated their professional skills and aspects of personality (attitudes towards pupils, self‐assuredness and well‐being) before and after the practicum. Forty‐six student teachers wrote daily semi‐structured diaries about essential learning situations during their practicum. Results indicate that in each practicum students improved significantly in preparing, conducting and post‐processing lessons. The mentors rated these changes as being greater than did the student teachers. From the perspective of the student teachers their general teaching skills also improved, and their attitudes toward pupils became more open. Furthermore, during practicum their self‐esteem and subjective well‐being increased. Diary data confirmed that there are no differences between different levels of practicum in terms of learning outcomes, but give some first insight into different ways of learning during internship.

Livelihood and Community Development: LforS learning and simulation game

Up to 15 people can participate in the game, which is supervised by a moderator. Households consisting of 1-5 people discuss options for diversification of household strategies. Aim of the game: By devising appropriate strategies, households seek to stand up to various types of events while improving their economic and social situation and, at the same time, taking account of ecological conditions. The annual General Community Meeting (GCM) provides an opportunity for households to create a general set-up at the local level that is more or less favourable to the strategies they are pursuing. The development of a community investment strategy, to be implemented by the GCM, and successful coordination between households will allow players to optimise their investments at the household level. The household who owns the most assets at the end of the game wins. Players participate very actively, as the game stimulates lively and interesting discussions. They find themselves confronted with different types of decision-making related to the reality of their daily lives. They explore different ways to model their own household strategies and discuss risks and opportunities. Reflections on the course of the game continually refer to the real-life situations of the participants.

Learning through Listening: Conversations for Strategic Change in a Healtcare Provider

The aim of this paper is investigate the role of conversation in strategic change so as to enhance both theory and practice in this respect. As an investigation on how conversations shape change processes in practice, we reflect on an interpretive case study in a health care organization. Through an OD project complemented by semi-structured interviews with participants, we gained a set of data and experiences that allows us to inquire into the relationship between conversations and change in more depth.

Regularization for sparsity in statistical analysis and machine learning

Pragmatism is the leading motivation of regularization. We can understand regularization as a modification of the maximum-likelihood estimator so that a reasonable answer could be given in an unstable or ill-posed situation. To mention some typical examples, this happens when fitting parametric or non-parametric models with more parameters than data or when estimating large covariance matrices. Regularization is usually used, in addition, to improve the bias-variance tradeoff of an estimation. Then, the definition of regularization is quite general, and, although the introduction of a penalty is probably the most popular type, it is just one out of multiple forms of regularization. In this dissertation, we focus on the applications of regularization for obtaining sparse or parsimonious representations, where only a subset of the inputs is used. A particular form of regularization, L1-regularization, plays a key role for reaching sparsity. Most of the contributions presented here revolve around L1-regularization, although other forms of regularization are explored (also pursuing sparsity in some sense). In addition to present a compact review of L1-regularization and its applications in statistical and machine learning, we devise methodology for regression, supervised classification and structure induction of graphical models. Within the regression paradigm, we focus on kernel smoothing learning, proposing techniques for kernel design that are suitable for high dimensional settings and sparse regression functions. We also present an application of regularized regression techniques for modeling the response of biological neurons. Supervised classification advances deal, on the one hand, with the application of regularization for obtaining a na¨ıve Bayes classifier and, on the other hand, with a novel algorithm for brain-computer interface design that uses group regularization in an efficient manner. Finally, we present a heuristic for inducing structures of Gaussian Bayesian networks using L1-regularization as a filter. El pragmatismo es la principal motivación de la regularización. Podemos entender la regularización como una modificación del estimador de máxima verosimilitud, de tal manera que se pueda dar una respuesta cuando la configuración del problema es inestable. A modo de ejemplo, podemos mencionar el ajuste de modelos paramétricos o no paramétricos cuando hay más parámetros que casos en el conjunto de datos, o la estimación de grandes matrices de covarianzas. Se suele recurrir a la regularización, además, para mejorar el compromiso sesgo-varianza en una estimación. Por tanto, la definición de regularización es muy general y, aunque la introducción de una función de penalización es probablemente el método más popular, éste es sólo uno de entre varias posibilidades. En esta tesis se ha trabajado en aplicaciones de regularización para obtener representaciones dispersas, donde sólo se usa un subconjunto de las entradas. En particular, la regularización L1 juega un papel clave en la búsqueda de dicha dispersión. La mayor parte de las contribuciones presentadas en la tesis giran alrededor de la regularización L1, aunque también se exploran otras formas de regularización (que igualmente persiguen un modelo disperso). Además de presentar una revisión de la regularización L1 y sus aplicaciones en estadística y aprendizaje de máquina, se ha desarrollado metodología para regresión, clasificación supervisada y aprendizaje de estructura en modelos gráficos. Dentro de la regresión, se ha trabajado principalmente en métodos de regresión local, proponiendo técnicas de diseño del kernel que sean adecuadas a configuraciones de alta dimensionalidad y funciones de regresión dispersas. También se presenta una aplicación de las técnicas de regresión regularizada para modelar la respuesta de neuronas reales. Los avances en clasificación supervisada tratan, por una parte, con el uso de regularización para obtener un clasificador naive Bayes y, por otra parte, con el desarrollo de un algoritmo que usa regularización por grupos de una manera eficiente y que se ha aplicado al diseño de interfaces cerebromáquina. Finalmente, se presenta una heurística para inducir la estructura de redes Bayesianas Gaussianas usando regularización L1 a modo de filtro.

Fusion of probabilistic knowledge-based classification rules and learning automata for automatic recognition of digital images

In this paper, the fusion of probabilistic knowledge-based classification rules and learning automata theory is proposed and as a result we present a set of probabilistic classification rules with self-learning capability. The probabilities of the classification rules change dynamically guided by a supervised reinforcement process aimed at obtaining an optimum classification accuracy. This novel classifier is applied to the automatic recognition of digital images corresponding to visual landmarks for the autonomous navigation of an unmanned aerial vehicle (UAV) developed by the authors. The classification accuracy of the proposed classifier and its comparison with well-established pattern recognition methods is finally reported.

Machine Learning in Scientometrics

El aprendizaje automático y la cienciometría son las disciplinas científicas que se tratan en esta tesis. El aprendizaje automático trata sobre la construcción y el estudio de algoritmos que puedan aprender a partir de datos, mientras que la cienciometría se ocupa principalmente del análisis de la ciencia desde una perspectiva cuantitativa. Hoy en día, los avances en el aprendizaje automático proporcionan las herramientas matemáticas y estadísticas para trabajar correctamente con la gran cantidad de datos cienciométricos almacenados en bases de datos bibliográficas. En este contexto, el uso de nuevos métodos de aprendizaje automático en aplicaciones de cienciometría es el foco de atención de esta tesis doctoral. Esta tesis propone nuevas contribuciones en el aprendizaje automático que podrían arrojar luz sobre el área de la cienciometría. Estas contribuciones están divididas en tres partes: Varios modelos supervisados (in)sensibles al coste son aprendidos para predecir el éxito científico de los artículos y los investigadores. Los modelos sensibles al coste no están interesados en maximizar la precisión de clasificación, sino en la minimización del coste total esperado derivado de los errores ocasionados. En este contexto, los editores de revistas científicas podrían disponer de una herramienta capaz de predecir el número de citas de un artículo en el fututo antes de ser publicado, mientras que los comités de promoción podrían predecir el incremento anual del índice h de los investigadores en los primeros años. Estos modelos predictivos podrían allanar el camino hacia nuevos sistemas de evaluación. Varios modelos gráficos probabilísticos son aprendidos para explotar y descubrir nuevas relaciones entre el gran número de índices bibliométricos existentes. En este contexto, la comunidad científica podría medir cómo algunos índices influyen en otros en términos probabilísticos y realizar propagación de la evidencia e inferencia abductiva para responder a preguntas bibliométricas. Además, la comunidad científica podría descubrir qué índices bibliométricos tienen mayor poder predictivo. Este es un problema de regresión multi-respuesta en el que el papel de cada variable, predictiva o respuesta, es desconocido de antemano. Los índices resultantes podrían ser muy útiles para la predicción, es decir, cuando se conocen sus valores, el conocimiento de cualquier valor no proporciona información sobre la predicción de otros índices bibliométricos. Un estudio bibliométrico sobre la investigación española en informática ha sido realizado bajo la cultura de publicar o morir. Este estudio se basa en una metodología de análisis de clusters que caracteriza la actividad en la investigación en términos de productividad, visibilidad, calidad, prestigio y colaboración internacional. Este estudio también analiza los efectos de la colaboración en la productividad y la visibilidad bajo diferentes circunstancias. ABSTRACT Machine learning and scientometrics are the scientific disciplines which are covered in this dissertation. Machine learning deals with the construction and study of algorithms that can learn from data, whereas scientometrics is mainly concerned with the analysis of science from a quantitative perspective. Nowadays, advances in machine learning provide the mathematical and statistical tools for properly working with the vast amount of scientometrics data stored in bibliographic databases. In this context, the use of novel machine learning methods in scientometrics applications is the focus of attention of this dissertation. This dissertation proposes new machine learning contributions which would shed light on the scientometrics area. These contributions are divided in three parts: Several supervised cost-(in)sensitive models are learned to predict the scientific success of articles and researchers. Cost-sensitive models are not interested in maximizing classification accuracy, but in minimizing the expected total cost of the error derived from mistakes in the classification process. In this context, publishers of scientific journals could have a tool capable of predicting the citation count of an article in the future before it is published, whereas promotion committees could predict the annual increase of the h-index of researchers within the first few years. These predictive models would pave the way for new assessment systems. Several probabilistic graphical models are learned to exploit and discover new relationships among the vast number of existing bibliometric indices. In this context, scientific community could measure how some indices influence others in probabilistic terms and perform evidence propagation and abduction inference for answering bibliometric questions. Also, scientific community could uncover which bibliometric indices have a higher predictive power. This is a multi-output regression problem where the role of each variable, predictive or response, is unknown beforehand. The resulting indices could be very useful for prediction purposes, that is, when their index values are known, knowledge of any index value provides no information on the prediction of other bibliometric indices. A scientometric study of the Spanish computer science research is performed under the publish-or-perish culture. This study is based on a cluster analysis methodology which characterizes the research activity in terms of productivity, visibility, quality, prestige and international collaboration. This study also analyzes the effects of collaboration on productivity and visibility under different circumstances.

Implementación de espirales de conocimiento y liderazgo situacional en la metodología b-learning

Comunicación presentada en las X Jornadas de Redes de Investigación en Docencia Universitaria, Alicante, 16-17 junio 2012.

O contributo dos portais digitais em contexto educativo no 1º ciclo do ensino básico

Relatório de Estágio apresentado à Escola Superior de Educação de Castelo Branco do Instituto Politécnico de Castelo Branco para cumprimento dos requisitos necessários à obtenção do grau de Mestre em Educação Pré-escolar e Ensino do 1º ciclo do Ensino Básico.

Prática de ensino supervisionada em Educação Pré-escolar e Ensino do 1.º Ciclo do Ensino Básico

O presente relatório foi concretizado no âmbito da Unidade Curricular da Prática de Ensino Supervisionada (PES), integrada no curso de Mestrado em Educação Pré-Escolar (EPE) e Ensino do 1.º Ciclo do Ensino Básico (1.º CEB). A prática educativa desenvolvida no contexto da EPE decorreu numa instituição Particular de Solidariedade Social, com um grupo de 12 crianças, com idades de 4 e 5 anos. No âmbito do contexto do 1.º CEB, a ação pedagógica decorreu num agrupamento de escolas pertencente à rede pública, com um grupo de 18 crianças do 2.º ano de escolaridade, com idades de 6 e 7 anos. Em ambos os contextos, desenvolvemos a ação educativa com o intuito de responder às necessidades e interesses das crianças sendo que tivemos o cuidado de criar um ambiente propício ao desenvolvimento e aprendizagem de saberes de forma lúdica, por gosto e prazer, onde, no dia-a-dia e ao longo da concretização das experiências de ensino/aprendizagem, prevalecesse o diálogo, a escuta, a negociação, a tomada de decisões e a resolução de problemas, de maneira a valorizarmos as crianças como cidadãos ativos, autónomos, responsáveis e capazes de saber fazer, ser e estar. Após definirmos as questões e os objetivos que iriam orientar a nossa investigação, foi fundamental delinearmos um estudo centrado nas abordagens metodológicas qualitativa e quantitativa. Neste sentido, para que fosse possível recolhermos dados que sustentassem o nosso estudo, recorremos a um conjunto de técnicas e instrumentos de recolha de dados, em ambos os contextos, designadamente: à observação participante, às notas de campo e aos registos fotográficos, às produções das crianças, ao inquérito por questionário e, ainda, à entrevista semiestruturada. Desta forma, ao longo da prática educativa, considerando as experiências de ensino/aprendizagem sustentadoras da nossa temática de estudo, procuramos promover atividades que envolvessem o contacto e exploração de diferentes suportes de escrita e leitura do meio envolvente, desafiando, apoiando e incentivando as crianças a desenvolverem o gosto e prazer pela leitura e escrita. Em relação à análise e interpretação das entrevistas semiestruturadas e dos inquéritos por questionário, dirigidas ao grupo de crianças da EPE e do 1.º CEB, respetivamente, percebemos que as crianças inquiridas estavam inseridas num ambiente educativo e familiar que, na sua rotina diária, desenvolvia práticas de literacia diversificadas e que potenciava o contacto com diferentes suportes de escrita e leitura. Com efeito, ao longo da nossa ação, assumimos uma atitude crítica e reflexiva, de modo a responder às necessidades e interesses das crianças, alicerçada em diferentes modos de pensar e agir.

Prática de ensino supervisionada em Educação Pré-escolar e Ensino do 1.º Ciclo do Ensino Básico

Este relatório de estágio pretende apresentar parte do trabalho desenvolvido no âmbito da Unidade Curricular de Prática de Ensino Supervisionada (PES), integrada no curso de Mestrado em educação pré-escolar e ensino do 1.º ciclo do ensino básico. A prática no contexto da educação pré-escolar foi realizada numa instituição pública com crianças de 3, 4 e 5 anos de idade. Em contexto do 1.º ciclo do ensino básico, a mesma decorreu numa escola da rede pública com um grupo/turma de crianças de 7 e 8 anos de idade, a frequentarem o 2.º ano de escolaridade. Nos dois contextos, a prática foi desenvolvida no sentido de responder aos interesses e necessidades das crianças, sendo que as atividades propostas visaram uma aprendizagem realizada através da pesquisa, reflexão e descoberta, pretendendo proporcionar às crianças momentos de aprendizagens significativas, ativas e socializadoras. Neste trabalho, para além da descrição e reflexão em torno da nossa ação em contexto (corporizadas através das experiências de ensino e aprendizagem) apresentamos dados que dizem respeito a uma investigação que desenvolvemos ao longo deste processo e que se fundamenta em alguns dos pressupostos pedagógicos defendidos pelo Movimento da Escola Moderna (MEM), nomeadamente sobre os instrumentos de regulação e monitorização/pilotagem da aprendizagem, tendo sido também realizada, para o efeito, uma revisão da literatura neste âmbito. Neste sentido, a nossa investigação tem como tema Dispositivos de mediação: monotorização da ação através dos instrumentos de regulação e pilotagem, e a opção metodológica desta investigação recai sobre uma abordagem qualitativa, tendo como técnicas de recolha de dados uma entrevista semiestruturada realizada às crianças e a observação direta e participante, com recurso a notas de campo e registos fotográficos. Das principais conclusões da investigação salientamos que existem instrumentos de regulação e pilotagem nas salas de aula, mas que os mesmos não são trabalhados de forma a que as crianças entendam o seu objetivo, adquiram autonomia de registo, recebam o feedback do seu impacto para a realização de aprendizagens e não usufruem das suas potencialidades pedagógicas.