The identification of urban locations with a high risk of diseases infections is a central aspect of public policies aiming at controlling these diseases. The presence of diseases, such as dengue fever, can be attributed to environmental factors in the urban scenario. Previous works have leveraged street-level imagery to provide estimates of dengue rates in an urban setting. In this paper, we apply Dense Deep Convolutional Neural Networks to both street-level and aerial imagery, providing evidence that aerial photography can provide better results than street-level images alone, while combining both leads to further improvements.

Convolutional Neural Networks are based on the hierarchical extraction of features over many layers, by using convolutional filters, or kernels. Each kernel is coded by a set of weights, which represents a feature to be extracted from the input. On a given layer, it is undesirable to have redundant kernels and the training algorithm must learn to differentiate them. SpreadOut is a kernel weight initializer that differentiates kernels before training, so as to improve convergence rates. It does so by maximizing a distance metric calculated over all pairs of kernels on the same layer, after weights are initialized by a traditional technique. We show that SpreadOut improves convergence rates on several benchmark datasets when compared to traditional approaches.

The ability to identify urban locations with a high risk of diseases infections is a central aspect of public policies aiming at controlling these diseases. In this paper, we investigate the use of street-level images, such as those from Google Street View, along with Convolutional Neural Networks to predict Dengue Fever (DF) and Dengue Hemorrhagic Fever (DHF) rates in urban locations. We conduct a case study in the city of Rio De Janeiro, Brazil, using the proposed methodology and DF/DHF data between the years of 2010 to 2014. We compare two Siamesebased CNNs, yielding an overall accuracy of 67% for 20,400 different locations. We conclude that street-level images are useful for the problem.

We explore a type of transfer learning in Convolutional Neural Networks where a network trained on a primary representation of examples (e.g. photographs) is capable of generalizing to a secondary representation (e.g. sketches) without fully training on the latter. We show that the network is able to improve classification on classes for which no examples in the secondary representation were provided, an evidence that the model is exploiting and generalizing concepts learned from examples in the primary representation. We measure this lateral representation learning on a CNN trained on the ImageNet dataset and use overlapping classes in the TU-Berlin and Caltech- 256 datasets as secondary representations, showing that the effect can't be fully explained by the network learning newly specialized kernels. This phenomenon can potentially be used to train classes in domain adaptation tasks for which few examples in a target representation are available.

This work provides a study on how Convolutional Neural Networks, trained to identify objects primarily in photos, perform when applied to more abstract representations of the same objects. Our main goal is to better understand the generalization abilities of these networks and their learned inner representations. We show that both GoogLeNet and AlexNet networks are largely unable to recognize abstract sketches that are easily recognizable by humans. Moreover, we show that the measured efficacy vary considerably across different classes and we discuss possible reasons for this.

This paper studies the use of Convolutional Neural Networks to automatically detect and classify diseases, nutritional deficiencies and damage by herbicides on apple trees from images of their leaves. This task is fundamental to guarantee a high quality of the resulting yields and is currently largely performed by experts in the field, which can severely limit scale and add to costs. By using a novel data set containing labeled examples consisting of 2539 images from 6 known disorders, we show that trained Convolutional Neural Networks are able to match or outperform experts in this task, achieving a 97.3% accuracy on a hold-out set.

Uniquely identifying individuals using anthropometric and gait data allows for passive biometric systems, where cooperation from the subjects being identified is not required. In this paper, we report on experiments using a novel data set composed of 140 individuals walking in front of a Microsoft Kinect sensor. We provide a methodology to extract anthropometric and gait features from this data and show results of applying different machine learning algorithms on subject identification tasks. Focusing on KNN classifiers, we discuss how accuracy varies in different settings, including number of individuals in a gallery, types of attributes used and number of considered neighbors. Finally, we compare the obtained results with other results in the literature, showing that our approach has comparable accuracy for large galleries.

In this paper, we analyze the dependency between centrality and individual performance in socially-inspired problem-solving systems. By means of extensive numerical simulations, we investigate how individual performance in four different models correlate with four different classical centrality measures. Our main result shows that there is a high linear correlation between centrality and individual performance when individuals systematically exploit central positions. In this case, central individuals tend to deviate from the expected majority contribution behavior. Although there is ample evidence about the relevance of centrality in social problem-solving, our work contributes to understand that some measures correlate better with individual performance than others due to individual traits, a position that is gaining strength in recent studies.

Identifying individuals using biometric data is an important task in surveillance, authentication and even entertainment. This task is more challenging when required to be performed without physical contact and at a distance. Analyzing video footages from individuals for patterns is an active area of research aiming at fulfilling this goal. We describe results on classifiers trained to identify individuals from data collected from 140 subjects walking in front of a Microsoft Kinect sensor, which allows tracking 3D points representing a subject's skeleton. From this data we extract anthropometric and gait attributes to be used by the classifiers. We show that anthropometric features are more important than gait features but using both allows for higher accuracies. Additionally, we explore how different numbers of subjects and numbers of available examples affect accuracy, providing evidences on how effective the proposed methodology can be in different scenarios.

Social interactions have recently been used as an inspiration for novel agent-based problem-solving models. Particle Swarm Optimization and Memetic Networks are two such algorithms. Although they draw inspiration from different real-world social systems, they both rely on the concept of a social network to regulate the internal information flow in a structured way. In this paper, we systematically investigate how a heterogeneous population composed of individuals from these two models behave as the system seeks the solution to the benchmark problems. We report on extensive numerical simulations, showing that this heterogeneous model is able to converge faster in two highly multimodal scenarios while being otherwise statistically equivalent to the original homogeneous models. Our results provide supportive evidence for the hypothesis that higher diversity in populations of problem-solvers can be beneficial and also adds a new dimension to previous heterogeneous problem-solving models.

We provide a study of crowdsourced design based on the popular service 99designs, a website where users create design contests for other users to submit their ideas for evaluation, competing for a monetary amount offered. By quantitatively analyzing a large number of contests, we report on the dynamics of the interactions between contests and designers. We show results on the effects of different financial incentives and contests' properties on the number and quality of submissions, as well as on how rewards are distributed across designers. We find that higher financial incentives do not translate to more effort by individual designers, but nonetheless have an impact on the quality outcome of contests by attracting a larger pool of designers. We also show that a majority of contests are dominated by a disproportionate few designers, which are both more active and effective in the service.

Recently, the use of social and human computing has witnessed increasing interest in the AI community. However, in order to harness the true potential of social computing, human subjects must play an active role in achieving computation in social networks and related media. Our work proposes an initial desiderata for effective social computing, drawing inspiration from artificial intelligence. Extensive experimentation reveals that several open issues and research questions have to be answered before the true potential of social and human computing is achieved. We, however, take a somewhat novel approach, by implementing a social networks environment where human subjects cooperate towards computational problem solving. In our social environment, human and artificial agents cooperate in their computation tasks, which may lead to a single problem-solving social network that potentially allows seamless cooperation among human and machine agents.

We propose a framework where humans and computers can collaborate seamlessly to solve problems. We do so by developing and applying a network model, namely Memenets, where human knowledge and reasoning are combined with machine computation to achieve problem-solving. The development of a Memenet is done in three steps: first, we simulate a machine-only network, as previous results have shown that memenets are efficient problem-solvers. Then, we perform an experiment with human agents organized in a online network. This allows us to investigate human behavior while solving problems in a social network and to postulate principles of agent communication in Memenets. These postulates describe an initial theory of how human-computer interaction functions inside social networks. In the third stage, postulates of step two allow one to combine human and machine computation to propose an integrated Memenet-based problem-solving computing model.

The use of resources in multiagent learning systems is a relevant research problem, with a number of applications in resource allocation, communication and synchronization. Multiagent distributed resource allocation requires that agents act on limited, localized information with minimum communication overhead in order to optimize the distribution of available resources. When requirements and constraints are dynamic, learning agents may be needed to allow for adaptation. One way of accomplishing learning is to observe past outcomes, using such information to improve future decisions. When limits in agents' memory or observation capabilities are assumed, one must decide on how large should the observation window be. We investigate how this decision influences both agents' and system's performance in the context of a special class of distributed resource allocation problems, namely dispersion games. We show by using several numerical experiments over a specific dispersion game (the Minority Game) that in such scenario an agent's performance is non-monotonically correlated with her memory size when all other agents are kept unchanged. We then provide an information-theoretic explanation for the observed behaviors, showing that a downward causation effect takes place.

This paper illustrates the use of a novel class of population-based optimization algorithms namely \textsl{Memetic Networks}. These algorithms make use of an underlying network to structure information flow between multiple individuals representing points in the search space. Memetic Networks have as a fundamental characteristic the possibility to aggregate several solutions in order to compose new ones. Network properties allow to control how information is spread among the population. We apply these algorithms to several real-valued benchmark optimization problems and the TSP and report results from extensive simulations. We show how some network properties can influence the algorithm's performance and illustrate the effectiveness of this new class of algorithms.

Memetic networks are a new class of population-based optimization algorithms that makes use of an underlying network to structure information flow between individuals representing points in the search space. Its main characteristic is the possibility of aggregating several solutions in order to compose new ones and the use of an explicit network to aid search. Algorithms from this class can be used to relate network properties to search performance in optimization tasks. We propose and report on algorithms applied to several benchmark optimization problems. We further show how some network properties - in particular, the existence of hubs - can influence the algorithm's performance.

We report experiments in a boundedly rational evolutionary game, namely the minority game, where agents apply a very simple learning algorithm to discard bad strategies and create new ones. The results show that even such simplified learning model presents qualitative differences from the behavior of the traditional game, where strategies are fixed and cannot be modified or discarded. We show that this result is qualitatively similar to other, more complex, learning approaches. Also, we study how the learning parameters of our model affect the dynamics of the game and we provide experimental evidence of a high dependence between the behavior of the system and the way fitness is attributed as new strategies enter the game.