In this paper, we introduce a novel combined reward cum penalty loss function to handle the regression problem. The proposed combined reward cum penalty loss function penalizes the data points which lie outside the $\epsilon$-tube of the regressor and also assigns reward for the data points which lie inside of the $\epsilon$-tube of the regressor. The combined reward cum penalty loss function based regression (RP-$\epsilon$-SVR) model has several interesting properties which are investigated in this paper and are also supported with the experimental results.

The Predictive Normalized Maximum Likelihood (pNML) scheme has been recently suggested for universal learning in the individual setting, where both the training and test samples are individual data. The goal of universal learning is to compete with a ``genie'' or reference learner that knows the data values, but is restricted to use a learner from a given model class. The pNML minimizes the associated regret for any possible value of the unknown label. Furthermore, its min-max regret can serve as a pointwise measure of learnability for the specific training and data sample. In this work we examine the pNML and its associated learnability measure for the Deep Neural Network (DNN) model class. As shown, the pNML outperforms the commonly used Empirical Risk Minimization (ERM) approach and provides robustness against adversarial attacks. Together with its learnability measure it can detect out of distribution test examples, be tolerant to noisy labels and serve as a confidence measure for the ERM. Finally, we extend the pNML to a ``twice universal'' solution, that provides universality for model class selection and generates a learner competing with the best one from all model classes.

Mobile context determination is an important step for many context aware services such as location-based services, enterprise policy enforcement, building or room occupancy detection for power or HVAC operation, etc. Especially in enterprise scenarios where policies (e.g., attending a confidential meeting only when the user is in "Location X") are defined based on mobile context, it is paramount to verify the accuracy of the mobile context. To this end, two stochastic models based on the theory of Hidden Markov Models (HMMs) to obtain mobile context are proposed-personalized model (HPContext) and collaborative filtering model (HCFContext). The former predicts the current context using sequential history of the user's past context observations, the latter enhances HPContext with collaborative filtering features, which enables it to predict the current context of the primary user based on the context observations of users related to the primary user, e.g., same team colleagues in company, gym friends, family members, etc. Each of the proposed models can also be used to enhance or complement the context obtained from sensors. Furthermore, since privacy is a concern in collaborative filtering, a privacy-preserving method is proposed to derive HCFContext model parameters based on the concepts of homomorphic encryption. Finally, these models are thoroughly validated on a real-life dataset.

Thanks to the recent advances in processing speed and data acquisition and storage, machine learning (ML) is penetrating every facet of our lives, and transforming research in many areas in a fundamental manner. Wireless communications is another success story -- ubiquitous in our lives, from handheld devices to wearables, smart homes, and automobiles. While recent years have seen a flurry of research activity in exploiting ML tools for various wireless communication problems, the impact of these techniques in practical communication systems and standards is yet to be seen. In this paper, we review some of the major promises and challenges of ML in wireless communication systems, focusing mainly on the physical layer. We present some of the most striking recent accomplishments that ML techniques have achieved with respect to classical approaches, and point to promising research directions where ML is likely to make the biggest impact in the near future. We also highlight the complementary problem of designing physical layer techniques to enable distributed ML at the wireless network edge, which further emphasizes the need to understand and connect ML with fundamental concepts in wireless communications.

In current clinical practice, score-based mortality prediction systems, such as the series of the acute Predicting the risk of mortality for patients with acute physiology and chronic health evaluation (APACHE) scoring myocardial infarction (AMI) using electronic health records system, are widely used to help determine the treatment or (EHRs) data can help identify risky patients who might need medicine should be given to patients admitted into intensive more tailored care. In our previous work, we built care units (ICUs) [10]. Nevertheless, these scoring systems computational models to predict one-year mortality of patients have significant limitations, e.g., 1) they are often restricted to admitted to an intensive care unit (ICU) with AMI or post only few predictors; 2) they have poor generalizability and may myocardial infarction syndrome. Our prior work only used the be less precise when applied to specific subpopulations other structured clinical data from MIMIC-III, a publicly available than the original population used for the initial development; ICU clinical database. In this study, we enhanced our work by and 3) they need to be periodically recalibrated to reflect adding the word embedding features from free-text discharge changes in clinical practice and patient demographics [6].

Probabilistic programs are key to deal with uncertainty in e.g. controller synthesis. They are typically small but intricate. Their development is complex and error prone requiring quantitative reasoning over a myriad of alternative designs. To mitigate this complexity, we adopt counterexample-guided inductive synthesis (CEGIS) to automatically synthesise finite-state probabilistic programs. Our approach leverages efficient model checking, modern SMT solving, and counterexample generation at program level. Experiments on practically relevant case studies show that design spaces with millions of candidate designs can be fully explored using a few thousand verification queries.

We present RL-GAN-Net, where a reinforcement learning (RL) agent provides fast and robust control of a generative adversarial network (GAN). Our framework is applied to point cloud shape completion that converts noisy, partial point cloud data into a high-fidelity completed shape by controlling the GAN. While a GAN is unstable and hard to train, we circumvent the problem by (1) training the GAN on the latent space representation whose dimension is reduced compared to the raw point cloud input and (2) using an RL agent to find the correct input to the GAN to generate the latent space representation of the shape that best fits the current input of incomplete point cloud. The suggested pipeline robustly completes point cloud with large missing regions. To the best of our knowledge, this is the first attempt to train an RL agent to control the GAN, which effectively learns the highly nonlinear mapping from the input noise of the GAN to the latent space of point cloud. The RL agent replaces the need for complex optimization and consequently makes our technique real time. Additionally, we demonstrate that our pipelines can be used to enhance the classification accuracy of point cloud with missing data.

The nature of basketball is such that its most cathartic moment--when the ball goes decisively and irretrievably through the hoop--is the same every time. The ball piercing the basket is both a discrete event and a continuous waterfall of motion that, for active players, is constant throughout their careers. They shoot in practice, they shoot in the game, they shoot and shoot and shoot. The motion becomes so ingrained in their muscle memory that the gesture requires only its activation; everything else--the elevation, the aiming at the basket, the cocking of the elbow and the follow-through of the hand--is programmed. I found myself thinking about the waterfall of shots in the wake of one of the more dramatic ones in recent N.B.A. history: Damian Lillard, of the Portland Trail Blazers, hitting the game-winning, series-ending shot against the Oklahoma City Thunder in Game Five.

The Immigration Services Agency plans to strengthen its eligibility standards for Japanese-language schools, it was learned Saturday. The move comes as Japanese-language schools have been under fire for accepting many foreign students whose purpose is to work in Japan. The number of Japanese-language schools recognized by the government grew 1.6 times over the past five years to 749 as of April 2. The government late last year outlined plans to improve the quality of Japanese-language schools as part of efforts to bring in more foreign workers to the country. Under the agency's plan, the requirement for the average student attendance rate would be revised from the current 50 percent or more in a month to 70 percent or more in a period of seven months. Schools failing to meet the requirement would not be allowed to accept foreign students.

If you're looking for some mundane distractions to get you through the holiday period, Shukan Taishu (May 6-13) has got just the thing. Its "Reiwa Commemorative Edition" introduces unusual rides. Not to be outdone, a park in Tochigi has camels for the same purpose, as does another in Chiba offering elephant rides. At Hakkeijima Sea Paradise in Yokohama, visitors from age 10 (who can prove they can swim for a distance of 25 meters) may emulate the "boy on a dolphin" theme and ride atop a friendly beluga whale. Two-wheeled Segway personal transporters are available for inexpensive rental at Showa Memorial Park in the city of Tachikawa.