Nearly 85 percent of travel and hospitality professionals are using AI within their businesses, according to a recent survey by Tata Consultancy Services, which is based in India. So far, the use is largely limited to their information-technology departments, with 46 percent of companies saying they use it for functions such as processing bookings and credit-card transactions. But within four years, 60 percent of companies surveyed said that AI would expand to their marketing efforts - persuading you to book their products. Indeed, most of the AI firepower is reserved for the back-end systems designed to squeeze more profit out of an airline seat or hotel room, or to improve the efficiency of airport operations. For example, flight disruptions cost airlines billions each year, so airports are deploying AI systems to quickly deal with irregular operations.

It doesn't take a rocket scientist to know that the cutting-edge technologies known as artificial intelligence will transform many U.S. industries. But, it takes a savvy investor to sort through the technology's early possibilities. Even the biggest tech names have yet to see their AI-related revenue growth take off, and the market is still waiting to see any real pure-play AI stock plays. But the rapidly developing technologies are starting to contribute sales to a handful of companies, while driving others to modify their products and technology platforms to tap into AI's possibilities. At a basic level, artificial intelligence is the use of computer algorithms to attempt to replicate the human ability to learn, reason and make decisions.

CB Insights unveiled the AI 100--a list of 100 of the most promising private companies applying artificial intelligence algorithms across industries, from healthcare to auto to fintech--at the Innovation Summit today. The companies were selected from a pool of nearly 500 applicants and nominees based on several criteria, including data submitted by the companies, responses to interview questions, technology focus, investor profile, team profile, mosaic scores, and funding history. "From financial services to healthcare to transport, incumbent companies in every industry are seeing that AI will reshape their industries. And as so often happens, transformational innovation comes from emerging companies. In the case of AI, a lot of the groundbreaking work is being done by the AI 100. The companies in the AI 100 are accelerating research, improving efficiency, and making many game-changing advancements that will be felt for decades to come," CB Insights CEO Anand Sanwal said in a press release.

A new study has suggested that a great personality trumps good looks when finding a match. Researchers found that people's perceptions of potential dates' attractiveness goes up after they have a positive face-to-face interaction - but only for those who were rated mid to low attractiveness based on their photo. Because those who were deemed good looking could not increase in attractiveness, it was those in the middle who received higher ratings for being friendly and having a good sense of humor. Researchers found that people's perceptions of potential dates' attractiveness goes up after they have a positive face-to-face interaction - but only for those who were rated mid to low attractiveness based on their photo The recent study, conducted by researchers at the University of Kansas, investigated how a person's perception changes of person they'meet' on a dating app when they come face-to-face in real life. By rating someone's attractiveness before meeting them diminishes the rater's evaluation of that person afterward, probably because the rater is comparing their conversation partner to all the other potential partners they saw online.

The findings open a world of possibility for using AI, or machine learning, to treat disease, researchers said. David Fleck, an associate professor at the UC College of Medicine, and his co-authors used artificial intelligence called "genetic fuzzy trees" to predict how bipolar patients would respond to lithium. Bipolar disorder, depicted in the TV show "Homeland" and the Oscar-winning "Silver Linings Playbook," affects as many as six million adults in the United States or 4 percent of the adult population in a given year. "In psychiatry, treatment of bipolar disorder is as much an art as a science," Fleck said. "Patients are fluctuating between periods of mania and depression. Treatments will change during those periods. It's really difficult to treat them appropriately during stages of the illness."

In this article, we extend the conventional framework of convolutional-Restricted-Boltzmann-Machine to learn highly abstract features among abitrary number of time related input maps by constructing a layer of multiplicative units, which capture the relations among inputs. In many cases, more than two maps are strongly related, so it is wise to make multiplicative unit learn relations among more input maps, in other words, to find the optimal relational-order of each unit. In order to enable our machine to learn relational order, we developed a reinforcement-learning method whose optimality is proven to train the network.

Kernel $k$-means clustering can correctly identify and extract a far more varied collection of cluster structures than the linear $k$-means clustering algorithm. However, kernel $k$-means clustering is computationally expensive when the non-linear feature map is high-dimensional and there are many input points. Kernel approximation, e.g., the Nystr\"om method, has been applied in previous works to approximately solve kernel learning problems when both of the above conditions are present. This work analyzes the application of this paradigm to kernel $k$-means clustering, and shows that applying the linear $k$-means clustering algorithm to $\frac{k}{\epsilon} (1 + o(1))$ features constructed using a so-called rank-restricted Nystr\"om approximation results in cluster assignments that satisfy a $1 + \epsilon$ approximation ratio in terms of the kernel $k$-means cost function, relative to the guarantee provided by the same algorithm without the use of the Nystr\"om method. As part of the analysis, this work establishes a novel $1 + \epsilon$ relative-error trace norm guarantee for low-rank approximation using the rank-restricted Nystr\"om approximation. Empirical evaluations on the $8.1$ million instance MNIST8M dataset demonstrate the scalability and usefulness of kernel $k$-means clustering with Nystr\"om approximation. This work argues that spectral clustering using Nystr\"om approximation---a popular and computationally efficient, but theoretically unsound approach to non-linear clustering---should be replaced with the efficient and theoretically sound combination of kernel $k$-means clustering with Nystr\"om approximation. The superior performance of the latter approach is empirically verified.

In this paper, we present a new approach to learning cascaded classifiers for use in computing environments that involve networks of heterogeneous and resource-constrained, low-power embedded compute and sensing nodes. We present a generalization of the classical linear detection cascade to the case of tree-structured cascades where different branches of the tree execute on different physical compute nodes in the network. Different nodes have access to different features, as well as access to potentially different computation and energy resources. We concentrate on the problem of jointly learning the parameters for all of the classifiers in the cascade given a fixed cascade architecture and a known set of costs required to carry out the computation at each node.To accomplish the objective of joint learning of all detectors, we propose a novel approach to combining classifier outputs during training that better matches the hard cascade setting in which the learned system will be deployed. This work is motivated by research in the area of mobile health where energy efficient real time detectors integrating information from multiple wireless on-body sensors and a smart phone are needed for real-time monitoring and delivering just- in-time adaptive interventions. We apply our framework to two activity recognition datasets as well as the problem of cigarette smoking detection from a combination of wrist-worn actigraphy data and respiration chest band data.

Vector autoregressive models characterize a variety of time series in which linear combinations of current and past observations can be used to accurately predict future observations. For instance, each element of an observation vector could correspond to a different node in a network, and the parameters of an autoregressive model would correspond to the impact of the network structure on the time series evolution. Often these models are used successfully in practice to learn the structure of social, epidemiological, financial, or biological neural networks. However, little is known about statistical guarantees on estimates of such models in non-Gaussian settings. This paper addresses the inference of the autoregressive parameters and associated network structure within a generalized linear model framework that includes Poisson and Bernoulli autoregressive processes. At the heart of this analysis is a sparsity-regularized maximum likelihood estimator. While sparsity-regularization is well-studied in the statistics and machine learning communities, those analysis methods cannot be applied to autoregressive generalized linear models because of the correlations and potential heteroscedasticity inherent in the observations. Sample complexity bounds are derived using a combination of martingale concentration inequalities and modern empirical process techniques for dependent random variables. These bounds, which are supported by several simulation studies, characterize the impact of various network parameters on estimator performance.

This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions. It is based on a tutorial given at ICASSP 2017. It introduces some recently proposed techniques of interpretation, along with theory, tricks and recommendations, to make most efficient use of these techniques on real data. It also discusses a number of practical applications.