Ensemble: an innovative approach to practice computer programming

Currently, the teaching-learning process in domains, such as computer programming, is characterized by an extensive curricula and a high enrolment of students. This poses a great workload for faculty and teaching assistants responsible for the creation, delivery, and assessment of student exercises. The main goal of this chapter is to foster practice-based learning in complex domains. This objective is attained with an e-learning framework—called Ensemble—as a conceptual tool to organize and facilitate technical interoperability among services. The Ensemble framework is used on a specific domain: computer programming. Content issues are tacked with a standard format to describe programming exercises as learning objects. Communication is achieved with the extension of existing specifications for the interoperation with several systems typically found in an e-learning environment. In order to evaluate the acceptability of the proposed solution, an Ensemble instance was validated on a classroom experiment with encouraging results.

High-Content Analysis of Breast Cancer Using Single-Cell Deep Transfer Learning

High-content analysis has revolutionized cancer drug discovery by identifying substances that alter the phenotype of a cell, which prevents tumor growth and metastasis. The high-resolution biofluorescence images from assays allow precise quantitative measures enabling the distinction of small molecules of a host cell from a tumor. In this work, we are particularly interested in the application of deep neural networks (DNNs), a cutting-edge machine learning method, to the classification of compounds in chemical mechanisms of action (MOAs). Compound classification has been performed using image-based profiling methods sometimes combined with feature reduction methods such as principal component analysis or factor analysis. In this article, we map the input features of each cell to a particular MOA class without using any treatment-level profiles or feature reduction methods. To the best of our knowledge, this is the first application of DNN in this domain, leveraging single-cell information. Furthermore, we use deep transfer learning (DTL) to alleviate the intensive and computational demanding effort of searching the huge parameter's space of a DNN. Results show that using this approach, we obtain a 30% speedup and a 2% accuracy improvement.

Adapter module for self-learning production systems

Dissertação para obtenção do Grau de Mestre em Engenharia Electrotécnica, Sistemas e Computadores

Learning facial-expression models with crowdsourcing

The computational power is increasing day by day. Despite that, there are some tasks that are still difficult or even impossible for a computer to perform. For example, while identifying a facial expression is easy for a human, for a computer it is an area in development. To tackle this and similar issues, crowdsourcing has grown as a way to use human computation in a large scale. Crowdsourcing is a novel approach to collect labels in a fast and cheap manner, by sourcing the labels from the crowds. However, these labels lack reliability since annotators are not guaranteed to have any expertise in the field. This fact has led to a new research area where we must create or adapt annotation models to handle these weaklylabeled data. Current techniques explore the annotators’ expertise and the task difficulty as variables that influences labels’ correction. Other specific aspects are also considered by noisy-labels analysis techniques. The main contribution of this thesis is the process to collect reliable crowdsourcing labels for a facial expressions dataset. This process consists in two steps: first, we design our crowdsourcing tasks to collect annotators labels; next, we infer the true label from the collected labels by applying state-of-art crowdsourcing algorithms. At the same time, a facial expression dataset is created, containing 40.000 images and respective labels. At the end, we publish the resulting dataset.

Métodos de aprendizagem automática: um estudo baseado na avaliação e previsão de clientes bancários

Data Mining surge, hoje em dia, como uma ferramenta importante e crucial para o sucesso de um negócio. O considerável volume de dados que atualmente se encontra disponível, por si só, não traz valor acrescentado. No entanto, as ferramentas de Data Mining, capazes de transformar dados e mais dados em conhecimento, vêm colmatar esta lacuna, constituindo, assim, um trunfo que ninguém quer perder. O presente trabalho foca-se na utilização das técnicas de Data Mining no âmbito da atividade bancária, mais concretamente na sua atividade de telemarketing. Neste trabalho são aplicados catorze algoritmos a uma base de dados proveniente do call center de um banco português, resultante de uma campanha para a angariação de clientes para depósitos a prazo com taxas de juro favoráveis. Os catorze algoritmos aplicados no caso prático deste projeto podem ser agrupados em sete grupos: Árvores de Decisão, Redes Neuronais, Support Vector Machine, Voted Perceptron, métodos Ensemble, aprendizagem Bayesiana e Regressões. De forma a beneficiar, ainda mais, do que a área de Data Mining tem para oferecer, este trabalho incide ainda sobre o redimensionamento da base de dados em questão, através da aplicação de duas estratégias de seleção de atributos: Best First e Genetic Search. Um dos objetivos deste trabalho prende-se com a comparação dos resultados obtidos com os resultados presentes no estudo dos autores Sérgio Moro, Raul Laureano e Paulo Cortez (Sérgio Moro, Laureano, & Cortez, 2011). Adicionalmente, pretende-se identificar as variáveis mais relevantes aquando da identificação do potencial cliente deste produto financeiro. Como principais conclusões, depreende-se que os resultados obtidos são comparáveis com os resultados publicados pelos autores mencionados, sendo os mesmos de qualidade e consistentes. O algoritmo Bagging é o que apresenta melhores resultados e a variável referente à duração da chamada telefónica é a que mais influencia o sucesso de campanhas similares.

Using data mining for prediction of hospital length of stay: an application of the CRISP-DM Methodology

Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.

Search improvements in multirelational learning

Machine learning, inductive logic programming, search

Neural dynamics and their relationship to learning behavior in response tot stimulation with a cortical neuroprosthesis

Sensory cortex, neuroprosthetics, brain-machine-interfaces, neurodynamics, learning, perception, embodied cognition

Dynamics of the recruitment of lateral amygdala neurons following successive fear learning to different conditional stimuli

In fear conditioning, an animal learns to associate an unconditioned stimulus (US), such as a shock, and a conditioned stimulus (CS), such as a tone, so that the presentation of the CS alone can trigger conditioned responses. Recent research on the lateral amygdala has shown that following cued fear conditioning, only a subset of higher-excitable neurons are recruited in the memory trace. Their selective deletion after fear conditioning results in a selective erasure of the fearful memory. I hypothesize that the recruitment of highly excitable neurons depends on responsiveness to stimuli, intrinsic excitability and local connectivity. In addition, I hypothesize that neurons recruited for an initial memory also participate in subsequent memories, and that changes in neuronal excitability affect secondary fear learning. To address these hypotheses, I will show that A) a rat can learn to associate two successive short-term fearful memories; B) neuronal populations in the LA are competitively recruited in the memory traces depending on individual neuronal advantages, as well as advantages granted by the local network. By performing two successive cued fear conditioning experiments, I found that rats were able to learn and extinguish the two successive short-term memories, when tested 1 hour after learning for each memory. These rats were equipped with a system of stable extracellular recordings that I developed, which allowed to monitor neuronal activity during fear learning. 233 individual putative pyramidal neurons could modulate their firing rate in response to the conditioned tone (conditioned neurons) and/or non- conditioned tones (generalizing neurons). Out of these recorded putative pyramidal neurons 86 (37%) neurons were conditioned to one or both tones. More precisely, one population of neurons encoded for a shared memory while another group of neurons likely encoded the memories' new features. Notably, in spite of a successful behavioral extinction, the firing rate of those conditioned neurons in response to the conditioned tone remained unchanged throughout memory testing. Furthermore, by analyzing the pre-conditioning characteristics of the conditioned neurons, I determined that it was possible to predict neuronal recruitment based on three factors: 1) initial sensitivity to auditory inputs, with tone-sensitive neurons being more easily recruited than tone- insensitive neurons; 2) baseline excitability levels, with more highly excitable neurons being more likely to become conditioned; and 3) the number of afferent connections received from local neurons, with neurons destined to become conditioned receiving more connections than non-conditioned neurons. - En conditionnement de la peur, un animal apprend à associer un stimulus inconditionnel (SI), tel un choc électrique, et un stimulus conditionné (SC), comme un son, de sorte que la présentation du SC seul suffit pour déclencher des réflexes conditionnés. Des recherches récentes sur l'amygdale latérale (AL) ont montré que, suite au conditionnement à la peur, seul un sous-ensemble de neurones plus excitables sont recrutés pour constituer la trace mnésique. Pour apprendre à associer deux sons au même SI, je fais l'hypothèse que les neurones entrent en compétition afin d'être sélectionnés lors du recrutement pour coder la trace mnésique. Ce recrutement dépendrait d'un part à une activation facilité des neurones ainsi qu'une activation facilité de réseaux de neurones locaux. En outre, je fais l'hypothèse que l'activation de ces réseaux de l'AL, en soi, est suffisante pour induire une mémoire effrayante. Pour répondre à ces hypothèses, je vais montrer que A) selon un processus de mémoire à court terme, un rat peut apprendre à associer deux mémoires effrayantes apprises successivement; B) des populations neuronales dans l'AL sont compétitivement recrutées dans les traces mnésiques en fonction des avantages neuronaux individuels, ainsi que les avantages consentis par le réseau local. En effectuant deux expériences successives de conditionnement à la peur, des rats étaient capables d'apprendre, ainsi que de subir un processus d'extinction, pour les deux souvenirs effrayants. La mesure de l'efficacité du conditionnement à la peur a été effectuée 1 heure après l'apprentissage pour chaque souvenir. Ces rats ont été équipés d'un système d'enregistrements extracellulaires stables que j'ai développé, ce qui a permis de suivre l'activité neuronale pendant l'apprentissage de la peur. 233 neurones pyramidaux individuels pouvaient moduler leur taux d'activité en réponse au son conditionné (neurones conditionnés) et/ou au son non conditionné (neurones généralisant). Sur les 233 neurones pyramidaux putatifs enregistrés 86 (37%) d'entre eux ont été conditionnés à un ou deux tons. Plus précisément, une population de neurones code conjointement pour un souvenir partagé, alors qu'un groupe de neurones différent code pour de nouvelles caractéristiques de nouveaux souvenirs. En particulier, en dépit d'une extinction du comportement réussie, le taux de décharge de ces neurones conditionné en réponse à la tonalité conditionnée est resté inchangée tout au long de la mesure d'apprentissage. En outre, en analysant les caractéristiques de pré-conditionnement des neurones conditionnés, j'ai déterminé qu'il était possible de prévoir le recrutement neuronal basé sur trois facteurs : 1) la sensibilité initiale aux entrées auditives, avec les neurones sensibles aux sons étant plus facilement recrutés que les neurones ne répondant pas aux stimuli auditifs; 2) les niveaux d'excitabilité des neurones, avec les neurones plus facilement excitables étant plus susceptibles d'être conditionnés au son ; et 3) le nombre de connexions reçues, puisque les neurones conditionné reçoivent plus de connexions que les neurones non-conditionnés. Enfin, nous avons constaté qu'il était possible de remplacer de façon satisfaisante le SI lors d'un conditionnement à la peur par des injections bilatérales de bicuculline, un antagoniste des récepteurs de l'acide y-Aminobutirique.

Active Learning of Very-High Resolution Optical Imagery with SVM: Entropy vs Margin Sampling

An active learning method is proposed for the semi-automatic selection of training sets in remote sensing image classification. The method adds iteratively to the current training set the unlabeled pixels for which the prediction of an ensemble of classifiers based on bagged training sets show maximum entropy. This way, the algorithm selects the pixels that are the most uncertain and that will improve the model if added in the training set. The user is asked to label such pixels at each iteration. Experiments using support vector machines (SVM) on an 8 classes QuickBird image show the excellent performances of the methods, that equals accuracies of both a model trained with ten times more pixels and a model whose training set has been built using a state-of-the-art SVM specific active learning method

Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

Learning spatial filters for multispectral image segmentation

We present a novel filtering method for multispectral satellite image classification. The proposed method learns a set of spatial filters that maximize class separability of binary support vector machine (SVM) through a gradient descent approach. Regularization issues are discussed in detail and a Frobenius-norm regularization is proposed to efficiently exclude uninformative filters coefficients. Experiments carried out on multiclass one-against-all classification and target detection show the capabilities of the learned spatial filters.

Personalized modeling for drug concentration prediction using Support Vector Machine

Building a personalized model to describe the drug concentration inside the human body for each patient is highly important to the clinical practice and demanding to the modeling tools. Instead of using traditional explicit methods, in this paper we propose a machine learning approach to describe the relation between the drug concentration and patients' features. Machine learning has been largely applied to analyze data in various domains, but it is still new to personalized medicine, especially dose individualization. We focus mainly on the prediction of the drug concentrations as well as the analysis of different features' influence. Models are built based on Support Vector Machine and the prediction results are compared with the traditional analytical models.

Time Series Input Selection using Multiple Kernel Learning

In this paper we study the relevance of multiple kernel learning (MKL) for the automatic selection of time series inputs. Recently, MKL has gained great attention in the machine learning community due to its flexibility in modelling complex patterns and performing feature selection. In general, MKL constructs the kernel as a weighted linear combination of basis kernels, exploiting different sources of information. An efficient algorithm wrapping a Support Vector Regression model for optimizing the MKL weights, named SimpleMKL, is used for the analysis. In this sense, MKL performs feature selection by discarding inputs/kernels with low or null weights. The approach proposed is tested with simulated linear and nonlinear time series (AutoRegressive, Henon and Lorenz series).