Experience generalization for multi-agent reinforcement learning

On-line learning methods have been applied successfully in multi-agent systems to achieve coordination among agents. Learning in multi-agent systems implies in a non-stationary scenario perceived by the agents, since the behavior of other agents may change as they simultaneously learn how to improve their actions. Non-stationary scenarios can be modeled as Markov Games, which can be solved using the Minimax-Q algorithm a combination of Q-learning (a Reinforcement Learning (RL) algorithm which directly learns an optimal control policy) and the Minimax algorithm. However, finding optimal control policies using any RL algorithm (Q-learning and Minimax-Q included) can be very time consuming. Trying to improve the learning time of Q-learning, we considered the QS-algorithm. in which a single experience can update more than a single action value by using a spreading function. In this paper, we contribute a Minimax-QS algorithm which combines the Minimax-Q algorithm and the QS-algorithm. We conduct a series of empirical evaluation of the algorithm in a simplified simulator of the soccer domain. We show that even using a very simple domain-dependent spreading function, the performance of the learning algorithm can be improved.

An approach to implement data fusion techniques in wireless sensor networks using genetic machine learning algorithms

Wireless Sensor Networks (WSNs) can be used to monitor hazardous and inaccessible areas. In these situations, the power supply (e.g. battery) of each node cannot be easily replaced. One solution to deal with the limited capacity of current power supplies is to deploy a large number of sensor nodes, since the lifetime and dependability of the network will increase through cooperation among nodes. Applications on WSN may also have other concerns, such as meeting temporal deadlines on message transmissions and maximizing the quality of information. Data fusion is a well-known technique that can be useful for the enhancement of data quality and for the maximization of WSN lifetime. In this paper, we propose an approach that allows the implementation of parallel data fusion techniques in IEEE 802.15.4 networks. One of the main advantages of the proposed approach is that it enables a trade-off between different user-defined metrics through the use of a genetic machine learning algorithm. Simulations and field experiments performed in different communication scenarios highlight significant improvements when compared with, for instance, the Gur Game approach or the implementation of conventional periodic communication techniques over IEEE 802.15.4 networks. © 2013 Elsevier B.V. All rights reserved.

Aprendizagem Baseada em Problemas (PBL – Problem-Based Learning): estratégia para o ensino e aprendizagem de algoritmos e conteúdos computacionais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Combined active and semi-supervised learning using particle walking temporal dynamicscombined active and semi-supervised learning using particle walking temporal dynamics

Both Semi-Supervised Leaning and Active Learning are techniques used when unlabeled data is abundant, but the process of labeling them is expensive and/or time consuming. In this paper, those two machine learning techniques are combined into a single nature-inspired method. It features particles walking on a network built from the data set, using a unique random-greedy rule to select neighbors to visit. The particles, which have both competitive and cooperative behavior, are created on the network as the result of label queries. They may be created as the algorithm executes and only nodes affected by the new particles have to be updated. Therefore, it saves execution time compared to traditional active learning frameworks, in which the learning algorithm has to be executed several times. The data items to be queried are select based on information extracted from the nodes and particles temporal dynamics. Two different rules for queries are explored in this paper, one of them is based on querying by uncertainty approaches and the other is based on data and labeled nodes distribution. Each of them may perform better than the other according to some data sets peculiarities. Experimental results on some real-world data sets are provided, and the proposed method outperforms the semi-supervised learning method, from which it is derived, in all of them.

Semi-supervised learning for relevance feedback on image retrieval tasks

Relevance feedback approaches have been established as an important tool for interactive search, enabling users to express their needs. However, in view of the growth of multimedia collections available, the user efforts required by these methods tend to increase as well, demanding approaches for reducing the need of user interactions. In this context, this paper proposes a semi-supervised learning algorithm for relevance feedback to be used in image retrieval tasks. The proposed semi-supervised algorithm aims at using both supervised and unsupervised approaches simultaneously. While a supervised step is performed using the information collected from the user feedback, an unsupervised step exploits the intrinsic dataset structure, which is represented in terms of ranked lists of images. Several experiments were conducted for different image retrieval tasks involving shape, color, and texture descriptors and different datasets. The proposed approach was also evaluated on multimodal retrieval tasks, considering visual and textual descriptors. Experimental results demonstrate the effectiveness of the proposed approach.

In silico network topology-based prediction of gene essentiality

The identification of genes essential for survival is important for the understanding of the minimal requirements for cellular life and for drug design. As experimental studies with the purpose of building a catalog of essential genes for a given organism are time-consuming and laborious, a computational approach which could predict gene essentiality with high accuracy would be of great value. We present here a novel computational approach, called NTPGE (Network Topology-based Prediction of Gene Essentiality), that relies on the network topology features of a gene to estimate its essentiality. The first step of NTPGE is to construct the integrated molecular network for a given organism comprising protein physical, metabolic and transcriptional regulation interactions. The second step consists in training a decision-tree-based machine-learning algorithm on known essential and non-essential genes of the organism of interest, considering as learning attributes the network topology information for each of these genes. Finally, the decision-tree classifier generated is applied to the set of genes of this organism to estimate essentiality for each gene. We applied the NTPGE approach for discovering the essential genes in Escherichia coli and then assessed its performance. (C) 2007 Elsevier B.V. All rights reserved.

Aprendizado não-supervisionado em redes neurais pulsadas de base radial: um estudo da capacidade de agrupamento para a classificação de pixels

Redes neurais pulsadas - redes que utilizam uma codificação temporal da informação - têm despontado como uma promissora abordagem dentro do paradigma conexionista, emergente da ciência cognitiva. Um desses novos modelos é a rede neural pulsada com função de base radial, que é capaz de armazenar informação nos tempos de atraso axonais dos neurônios. Um algoritmo de aprendizado foi aplicado com sucesso nesta rede pulsada, que se mostrou capaz de mapear uma seqüência de pulsos de entrada em uma seqüência de pulsos de saída. Mais recentemente, um método baseado no uso de campos receptivos gaussianos foi proposto para codificar dados constantes em uma seqüência de pulsos temporais. Este método tornou possível a essa rede lidar com dados computacionais. O processo de aprendizado desta nova rede não se encontra plenamente compreendido e investigações mais profundas são necessárias para situar este modelo dentro do contexto do aprendizado de máquinas e também para estabelecer as habilidades e limitações desta rede. Este trabalho apresenta uma investigação desse novo classificador e um estudo de sua capacidade de agrupar dados em três dimensões, particularmente procurando estabelecer seus domínios de aplicação e horizontes no campo da visão computacional.

Variational studies and replica symmetry breaking in the generalization problem of the binary perceptron

We analyze the average performance of a general class of learning algorithms for the nondeterministic polynomial time complete problem of rule extraction by a binary perceptron. The examples are generated by a rule implemented by a teacher network of similar architecture. A variational approach is used in trying to identify the potential energy that leads to the largest generalization in the thermodynamic limit. We restrict our search to algorithms that always satisfy the binary constraints. A replica symmetric ansatz leads to a learning algorithm which presents a phase transition in violation of an information theoretical bound. Stability analysis shows that this is due to a failure of the replica symmetric ansatz and the first step of replica symmetry breaking (RSB) is studied. The variational method does not determine a unique potential but it allows construction of a class with a unique minimum within each first order valley. Members of this class improve on the performance of Gibbs algorithm but fail to reach the Bayesian limit in the low generalization phase. They even fail to reach the performance of the best binary, an optimal clipping of the barycenter of version space. We find a trade-off between a good low performance and early onset of perfect generalization. Although the RSB may be locally stable we discuss the possibility that it fails to be the correct saddle point globally. ©2000 The American Physical Society.

Improving the accuracy of the optimum-path forest supervised classifier for large datasets

In this work, a new approach for supervised pattern recognition is presented which improves the learning algorithm of the Optimum-Path Forest classifier (OPF), centered on detection and elimination of outliers in the training set. Identification of outliers is based on a penalty computed for each sample in the training set from the corresponding number of imputable false positive and false negative classification of samples. This approach enhances the accuracy of OPF while still gaining in classification time, at the expense of a slight increase in training time. © 2010 Springer-Verlag.

OPF-MRF: Optimum-path forest and Markov random fields for contextual-based image classification

Some machine learning methods do not exploit contextual information in the process of discovering, describing and recognizing patterns. However, spatial/temporal neighboring samples are likely to have same behavior. Here, we propose an approach which unifies a supervised learning algorithm - namely Optimum-Path Forest - together with a Markov Random Field in order to build a prior model holding a spatial smoothness assumption, which takes into account the contextual information for classification purposes. We show its robustness for brain tissue classification over some images of the well-known dataset IBSR. © 2013 Springer-Verlag.

Aplicação de redes neurais artificiais no monitoramento da operação de dressagem

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

NodePM: A Remote Monitoring Alert System for Energy Consumption Using Probabilistic Techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

An evolutionary approach to improve connectivity prediction in mobile wireless sensor networks

Connectivity is the basic factor for the proper operation of any wireless network. In a mobile wireless sensor network it is a challenge for applications and protocols to deal with connectivity problems, as links might get up and down frequently. In these scenarios, having knowledge of the node remaining connectivity time could both improve the performance of the protocols (e.g. handoff mechanisms) and save possible scarce nodes resources (CPU, bandwidth, and energy) by preventing unfruitful transmissions. The current paper provides a solution called Genetic Machine Learning Algorithm (GMLA) to forecast the remainder connectivity time in mobile environments. It consists in combining Classifier Systems with a Markov chain model of the RF link quality. The main advantage of using an evolutionary approach is that the Markov model parameters can be discovered on-the-fly, making it possible to cope with unknown environments and mobility patterns. Simulation results show that the proposal is a very suitable solution, as it overcomes the performance obtained by similar approaches.

Tool condition monitoring of aluminum oxide grinding wheel in dressing operation using acoustic emission and neural networks

The grinding operation gives workpieces their final finish, minimizing surface roughness through the interaction between the abrasive grains of a tool (grinding wheel) and the workpiece. However, excessive grinding wheel wear due to friction renders the tool unsuitable for further use, thus requiring the dressing operation to remove and/or sharpen the cutting edges of the worn grains to render them reusable. The purpose of this study was to monitor the dressing operation using the acoustic emission (AE) signal and statistics derived from this signal, classifying the grinding wheel as sharp or dull by means of artificial neural networks. An aluminum oxide wheel installed on a surface grinding machine, a signal acquisition system, and a single-point dresser were used in the experiments. Tests were performed varying overlap ratios and dressing depths. The root mean square values and two additional statistics were calculated based on the raw AE data. A multilayer perceptron neural network was used with the Levenberg-Marquardt learning algorithm, whose inputs were the aforementioned statistics. The results indicate that this method was successful in classifying the conditions of the grinding wheel in the dressing process, identifying the tool as "sharp''(with cutting capacity) or "dull''(with loss of cutting capacity), thus reducing the time and cost of the operation and minimizing excessive removal of abrasive material from the grinding wheel.

Segmentação interativa de imagens utilizando competição e cooperação entre partículas

Pós-graduação em Ciência da Computação - IBILCE