Convolutional neural networks (CNNs) have been used over the past years to solve many different artificial intelligence (AI) problems, providing significant advances in some domains and leading to state-of-the-art results. However, the topologies of CNNs involve many different parameters, and in most cases, their design remains a manual process that involves effort and a significant amount of trial and error. In this work, we have explored the application of neuroevolution to the automatic design of CNN topolo-gies, introducing a common framework for this task and developing two novel solutions based on ge-netic algorithms and grammatical evolution. We have evaluated our proposal using the MNIST dataset for handwritten digit recognition, achieving a result that is highly competitive with the state-of-the-art with-out any kind of data augmentation or preprocessing. When misclassified samples are carefully observed, it is found that most of them involve handwritten digits that are difficult to recognize even by a human.

This paper summarizes the top state-of-the-art contributions reported on the MNIST dataset for handwritten digit recognition. This dataset has been extensively used to validate novel techniques in computer vision, and in recent years, many authors have explored the performance of convolutional neural networks (CNNs) and other deep learning techniques over this dataset. To the best of our knowledge, this paper is the first exhaustive and updated review of this dataset; there are some online rankings, but they are outdated, and most published papers survey only closely related works, omitting most of the literature. This paper makes a distinction between those works using some kind of data augmentation and works using the original dataset out-of-the-box. Also, works using CNNs are reported separately; as they are becoming the state-of-the-art approach for solving this problem. Nowadays, a significant amount of works have attained a test error rate smaller than 1% on this dataset; which is becoming non-challenging. By mid-2017, a new dataset was introduced: EMNIST, which involves both digits and letters, with a larger amount of data acquired from a database different than MNIST's. In this paper, EMNIST is explained and some results are surveyed.

In this paper, we overview the 2009 Simulated Car Racing Championship-an event comprising three competitions held in association with the 2009 IEEE Congress on Evolutionary Computation (CEC), the 2009 ACM Genetic and Evolutionary Computation Conference (GECCO), and the 2009 IEEE Symposium on Computational Intelligence and Games (CIG). First, we describe the competition regulations and the software framework. Then, the five best teams describe the methods of computational intelligence they used to develop their drivers and the lessons they learned from the participation in the championship. The organizers provide short summaries of the other competitors. Finally, we summarize the championship results, followed by a discussion about what the organizers learned about 1) the development of high-performing car racing controllers and 2) the organization of scientific competitions

This work explores the connection between psychological well-being and Internet use in older adults. The study is based on a sample of 2314 participants in the English Longitudinal Study of Aging. The subjects, aged 50 years and older, were interviewed every two years over the 2006–2007 to 2014–2015 period. The connection between the use of Internet/Email and the main dimensions of psychological well-being (evaluative, hedonic and eudaimonic) was analyzed by means of three generalized estimating equation models that were fitted on 2-year lagged repeated measurements. The outcome variables, the scores on three well-being scales, were explained in terms of Internet/Email use, controlling for covariates that included health and socioeconomic indicators. The results support the existence of a direct relationship between Internet/Email use and psychological well-being. The connection between the main predictor and the score of the participants on the scale used to measure the eudaimonic aspect was positive and statistically significant at conventional levels (p-value: 0.015). However, the relevance of digital literacy on the evaluative and the hedonic components could not be confirmed (p-values for evaluative and hedonic dimensions were 0.078 and 0.192, respectively).

Abstract-This paper describes the simulated car racing competition held in association with the IEEE WCCI 2008 conference. The organization of the competition is described, along with the rules, the software used, and the submitted car racing controllers. The results of the competition are presented, followed by a discussion about what can be learned from this competition, both about learning controllers with evolutionary methods and about competition organization. The paper is coauthored by the organizers and participants of the competition.

Abstract-This work describes a proposal for developing and testing a scalable machine learning architecture able to provide real-time predictions or analytics as a service over domain-independent big data, working on top of the Hadoop ecosystem and providing real-time analytics as a service through a RESTful API. Systems implementing this architecture could provide companies with on-demand tools facilitating the tasks of storing, analyzing, understanding and reacting to their data, either in batch or stream fashion; and could turn into a valuable asset for improving the business performance and be a key market differentiator in this fast pace environment. In order to validate the proposed architecture, two systems are developed, each one providing classical machine-learning services in different domains: the first one involves a recommender system for web advertising, while the second consists in a prediction system which learns from gamers' behavior and tries to predict future events such as purchases or churning. An evaluation is carried out on these systems, and results show how both services are able to provide fast responses even when a number of concurrent requests are made, and in the particular case of the second system, results clearly prove that computed predictions significantly outperform those obtained if random guess was used.

Soft computing is progressively gaining presence in the financial world. The number of real and potential applications is very large and, accordingly, so is the presence of applied research papers in the literature. The aim of this paper is both to present relevant application areas, and to serve as an introduction to the subject. This paper provides arguments that justify the growing interest in these techniques among the financial community and introduces domains of application such as stock and currency market prediction, trading, portfolio management, credit scoring or financial distress prediction areas.

Abstract:The prediction of initial returns on initial public offerings (IPOs) is a complex matter. The independent variables identified in the literature mix strong and weak predictors, their explanatory power is limited, and samples include a sizable number of outliers. In this context, we suggest that random forests are a potentially powerful tool. In this paper, we benchmark this algorithm against a set of eight classic machine learning algorithms. The results of this comparison show that random forests outperform the alternatives in terms of mean and median predictive accuracy. The technique also provided the second smallest error variance among the stochastic algorithms. The experimental work also supports the potential of random forests for two practical applications: IPO pricing and IPO trading.