The notion of flat minima has played a key role in the generalization studies of deep learning models. However, existing definitions of the flatness are known to be sensitive to the rescaling of parameters. The issue suggests that the previous definitions of the flatness might not be a good measure of generalization, because generalization is invariant to such rescalings. In this paper, from the PAC-Bayesian perspective, we scrutinize the discussion concerning the flat minima and introduce the notion of normalized flat minima, which is free from the known scale dependence issues. Additionally, we highlight the scale dependence of existing matrix-norm based generalization error bounds similar to the existing flat minima definitions. Our modified notion of the flatness does not suffer from the insufficiency, either, suggesting it might provide better hierarchy in the hypothesis class.

In modern applications, we frequently encounter complex object-type data, such as functions (Ramsay and Silverman, 2006), trees (Wang and Marron, 2007), shapes (Srivastava et al., 2011), and networks (Durante et al., 2017). In many instances, such data are collected repeatedly under different conditions, with an additional response variable of interest available for each replicate. This has motivated an increasingly rich literature on generalizing regression on vector predictors to settings involving more elaborate object-type predictors with special characteristics, such as functions (James, 2002), manifolds (Nilsson et al., 2007), tensors (Zhou et al., 2013), and undirected networks (Guha and Rodriguez, 2018). Complex objects are often built recursively from simpler parts. In this article, we introduce a new class of object data, denoted composite objects (CO), which are structured data composed of primitive objects (POs). Many common data types can be seen as instances of the CO family, such as a collection of time-stamped events, connections between regions of the brain, or basketball shots on the court. The component POs in COtype data can be enormous and mostly distinctive from one another across replicates, presenting new challenges for data exploration, analysis, and visualization. We are interested in identifying the association between the patterns of coordinated interactions among individual units in a group and the performance of the group. In this article, we focus on analyzing the FIFA World Cup 2018 data collected by StatsBomb.

Fair clustering under the disparate impact doctrine requires that population of each protected group should be approximately equal in every cluster. Previous work investigated a difficult-to-scale pre-processing step for $k$-center and $k$-median style algorithms for the special case of this problem when the number of protected groups is two. In this work, we consider a more general and practical setting where there can be many protected groups. To this end, we propose Deep Fair Clustering, which learns a discriminative but fair cluster assignment function. The experimental results on three public datasets with different types of protected attribute show that our approach can steadily improve the degree of fairness while only having minor loss in terms of clustering quality.

In the industry of video content providers such as VOD and IPTV, predicting the popularity of video contents in advance is critical not only from a marketing perspective but also from a network optimization perspective. By predicting whether the content will be successful or not in advance, the content file, which is large, is efficiently deployed in the proper service providing server, leading to network cost optimization. Many previous studies have done view count prediction research to do this. However, the studies have been making predictions based on historical view count data from users. In this case, the contents had been published to the users and already deployed on a service server. These approaches make possible to efficiently deploy a content already published but are impossible to use for a content that is not be published. To address the problems, this research proposes a hybrid machine learning approach to the classification model for the popularity prediction of newly video contents which is not published. In this paper, we create a new variable based on the related content of the specific content and divide entire dataset by the characteristics of the contents. Next, the prediction is performed using XGBoosting and deep neural net based model according to the data characteristics of the cluster. Our model uses metadata for contents for prediction, so we use categorical embedding techniques to solve the sparsity of categorical variables and make them learn efficiently for the deep neural net model. As well, we use the FTRL-proximal algorithm to solve the problem of the view-count volatility of video content. We achieve overall better performance than the previous standalone method with a dataset from one of the top streaming service company.

Probability theory and Dempster-Shafer theory are two germane theories to represent and handle uncertain information. Recent study suggested a transformation to obtain the negation of a probability distribution based on the maximum entropy. Correspondingly, determining the negation of a belief structure, however, is still an open issue in Dempster-Shafer theory, which is very important in theoretical research and practical applications. In this paper, a negation transformation for belief structures is proposed based on maximum uncertainty allocation, and several important properties satisfied by the transformation have been studied. The proposed negation transformation is more general and could totally compatible with existing transformation for probability distributions.

Artificial intelligence is complicated; in this field, progress is, accordingly, difficult for the layman. The make to the Alphabet Holding company belonging to the AI Company deep mind has done in the past more frequently by in-game competitions against people the Superiority of its developments in order to demonstrate research progress. Up to this proof of the dominance in the year 2015, the traditional Board game was considered to be too complicated for machines. And the South Korean Lee Sedol as a more powerful opponent who was at least 18 Times champion of the world, and because of its unconventional and creative game in his home country a national hero. Although no one would be offended that a car can cover a distance faster than a human.

Robots aren't replacing everyone, but a quarter of US jobs will be severely disrupted as artificial intelligence accelerates the automation of existing work, according to a new Brookings Institution report. The report, published on Thursday, says roughly 36 million Americans hold jobs with "high exposure" to automation -- meaning at least 70% of their tasks could soon be performed by machines using current technology. Among those most likely to be affected are cooks, waiters and others in food services; short-haul truck drivers; and clerical office workers. "That population is going to need to upskill, reskill or change jobs fast," said Mark Muro, lead author of the report. Muro said the timeline for the changes could be "a few years or it could be two decades."

You might think that digital technologies, often considered a product of "the West", would hasten the divergence of Eastern and Western philosophies. But within the study of Vedanta, an ancient Indian school of thought, I see the opposite effect at work. Thanks to our growing familiarity with computing, virtual reality and artificial intelligence, "modern" societies are now better placed than ever to grasp the insights of this tradition. Vedanta summarises the metaphysics of the Upanishads, a clutch of Sanskrit religious texts, likely written between 800 and 500 BCE. They form the basis for the many philosophical, spiritual and mystical traditions of the Indian sub-continent.

Royal Dutch Shell is heavily investing in research and development of artificial intelligence (AI), which it hopes will provide solutions to some of its most pressing challenges. From meeting the demands of a transitioning energy market, urgently in need of cleaner and more efficient power, to improving safety on the forecourts of its service stations, AI is at the top of the agenda. I have been working with Shell over the past months to help create a data strategy, which gave me a thorough insight into Shell's AI priorities and initiatives. Current initiatives include deploying reinforcement learning in its exploration and drilling program, to reduce the cost of extracting the gas that still drives a significant proportion of its revenues. Elsewhere across its global business, Shell is rolling out AI at its public electric car charging stations, to manage the shifting demand for power throughout a day.

There is a really interesting concept in psychology called the Johari Window and it suggests that we rarely see ourselves as we actually are. Not only that, but we think other people see us differently than they do. Maybe you're not as charming as we think we are. Maybe that laughter after you told a joke was nervous laughter, but you thought you were hilarious. The key takeaway is that it's rare for people to accurately describe themselves to others as they actually are.