This paper proposes a novel method for optimal exposure operation in low quality images. The method uses reinforcement learning coupled with a discriminant loss (from GANs) to learn the optimal sequence of operations (i.e., the different exposures for each subimage component from a semantic segmentation of the input image) that generate, through a blender of all the components, a good quality - better exposed image. The main concern with this paper is the poor clarity of exposition. The formal definition of the image processing problem is lacking. Semantic segmentation is one major component but it's not discussed.

Aziz discusses the infrastructure necessary for brands to do sophisticated mobile advertising. Sramana Mitra: What do you do? Our view is that App Science is a gateway into understanding a consumer's behavior both from purchases as well as general behavior on mobile devices. Sramana Mitra: What, in the domain of artificial intelligence, is relevant? Aziz Rahim: Most of the folks in our industry have always looked at apps as current snapshots.

The use of artificial intelligence in sports isn't a major surprise, given the advancement in technology. Rise in computing power, availability of massive amount of data and an increased willingness of stakeholders to leverage such tools are the three principal reasons why the role of artificial intelligence in sports has gained a lot more importance recently. Someone who thinks the application of artificial intelligence in sports is limited to improving the performance of players is in for a pleasant shock. That's because there are many more avenues where AI is used. Here we list 9 applications that AI has found in the world of sports.

Tomorrow, key figures at leading Silicon Valley technology companies will appear on Capitol Hill. Twitter CEO Jack Dorsey, Facebook COO Sheryl Sandberg, and a Google representative (lawmakers want Alphabet CEO Larry Page, the company wants to send lawyer Kent Walker) will answer questions from various members of Congress about bias, artificial intelligence, and, we suspect, whether these mammoth companies should continue to be the dominant communication platforms for most Americans. Here are some of the main themes to look out for in the discussions--and one overarching question that really should frame the debate. Key question: Why shouldn't you be broken up? Background: The economic clout of the tech giants--and its implications for other areas of their influence--has sparked considerable debate already this year.

Tomorrow, key figures at leading Silicon Valley technology companies will appear on Capitol Hill. Twitter CEO Jack Dorsey, Facebook COO Sheryl Sandberg, and a Google representative (lawmakers want Alphabet CEO Larry Page, the company wants to send lawyer Kent Walker) will answer questions from various members of Congress about bias, artificial intelligence, and, we suspect, whether these mammoth companies should continue to be the dominant communication platforms for most Americans. Here are some of the main themes to look out for in the discussions--and one overarching question that really should frame the debate. Key question: Why shouldn't you be broken up? Background: The economic clout of the tech giants--and its implications for other areas of their influence--has sparked considerable debate already this year.

As artificial intelligence (AI) and machine learning are woven into banking's fold, their potential is almost too vast to predict. The real benefit is in financial institutions' ability to understand where and how it makes sense to apply these tools first, and where they can derive the greatest value in the fastest way. While a few industry leaders do get it, many discussions around artificial intelligence (AI) in banking shows that the industry at large still views AI in very abstract terms. While banks seem to be thinking about AI more and more, there still seems to be a consistent struggle in understanding when or where to apply this analytic tool. This struggle often leads to hesitation to actually testing and implementing the benefits of AI at financial institutions.

Mining sequential patterns on environment sensor data is a challenging task; the data can present noises and may also contain sparse patterns, which are difficult to be detected. The knowledge extracted from environment sensor data can be used to determine climate changes. However, there is a lack of methods that can handle this kind of database. In this paper, we propose a method to mine sequential patterns in sparse, incomplete and noisy sensor data. The proposed method, called Stretchy Time Windows (STW), allows the mining of sequential patterns that present time gaps between their events. We propose an algorithm to implement STW, called Miner of Stretchy Time Sequences (MSTS). The proposed algorithm works with sequences of any size and uses a balanced strategy to analyze the search space. Our experiments show that MSTS returns sequences that have a longer period of analysis than GSP a traditional frequent pattern mining algorithm. In fact, 5 times larger than GSP and higher number of patterns (2.3 times) when compared to previous methods.