We propose a simple yet powerful test statistic to quantify the discrepancy between two conditional distributions. The new statistic avoids the explicit estimation of the underlying distributions in highdimensional space and it operates on the cone of symmetric positive semidefinite (SPS) matrix using the Bregman matrix divergence. Moreover, it inherits the merits of the correntropy function to explicitly incorporate high-order statistics in the data. We present the properties of our new statistic and illustrate its connections to prior art. We finally show the applications of our new statistic on three different machine learning problems, namely the multi-task learning over graphs, the concept drift detection, and the information-theoretic feature selection, to demonstrate its utility and advantage. Code of our statistic is available at https://bit.ly/BregmanCorrentropy.

Many applications of Bayesian data analysis involve sensitive information such as personal documents or medical records, motivating methods which ensure that privacy is protected. We introduce a general privacy-preserving framework for Variational Bayes (VB), a widely used optimization-based Bayesian inference method. Our framework respects differential privacy, the gold-standard privacy criterion, and encompasses a large class of probabilistic models, called the Conjugate Exponential (CE) family. We observe that we can straightforwardly privatise VB's approximate posterior distributions for models in the CE family, by perturbing the expected sufficient statistics of the complete-data likelihood. For a broadly-used class of non-CE models, those with binomial likelihoods, we show how to bring such models into the CE family, such that inferences in the modified model resemble the private variational Bayes algorithm as closely as possible, using the Pólya-Gamma data augmentation scheme. The iterative nature of variational Bayes presents a further challenge since iterations increase the amount of noise needed. We overcome this by combining: (1) an improved composition method for differential privacy, called the moments accountant, which provides a tight bound on the privacy cost of multiple VB iterations and thus significantly decreases the amount of additive noise; and (2) the privacy amplification effect of subsampling mini-batches from large-scale data in stochastic learning. We empirically demonstrate the effectiveness of our method in CE and non-CE models including latent Dirichlet allocation, Bayesian logistic regression, and sigmoid belief networks, evaluated on real-world datasets.

In this paper, we study a joint detection, mapping and navigation problem for a single unmanned aerial vehicle (UAV) equipped with a low complexity radar and flying in an unknown environment. The goal is to optimize its trajectory with the purpose of maximizing the mapping accuracy and, at the same time, to avoid areas where measurements might not be sufficiently informative from the perspective of a target detection. This problem is formulated as a Markov decision process (MDP) where the UAV is an agent that runs either a state estimator for target detection and for environment mapping, and a reinforcement learning (RL) algorithm to infer its own policy of navigation (i.e., the control law). Numerical results show the feasibility of the proposed idea, highlighting the UAV's capability of autonomously exploring areas with high probability of target detection while reconstructing the surrounding environment.

Generative adversarial networks (GANs) have shown remarkable success in generation of data from natural data manifolds such as images. In several scenarios, it is desirable that generated data is well-clustered, especially when there is severe class imbalance. In this paper, we focus on the problem of clustering in generated space of GANs and uncover its relationship with the characteristics of the latent space. We derive from first principles, the necessary and sufficient conditions needed to achieve faithful clustering in the GAN framework: (i) presence of a multimodal latent space with adjustable priors, (ii) existence of a latent space inversion mechanism and (iii) imposition of the desired cluster priors on the latent space. We also identify the GAN models in the literature that partially satisfy these conditions and demonstrate the importance of all the components required, through ablative studies on multiple real world image datasets. Additionally, we describe a procedure to construct a multimodal latent space which facilitates learning of cluster priors with sparse supervision.

COVID-19 has created a global pandemic with high morbidity and mortality in 2020. Novel coronavirus (nCoV), also known as Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV2), is responsible for this deadly disease. International Committee on Taxonomy of Viruses (ICTV) has declared that nCoV is highly genetically similar to SARS-CoV epidemic in 2003 (89% similarity). Limited number of clinically validated Human-nCoV protein interaction data is available in the literature. With this hypothesis, the present work focuses on developing a computational model for nCoV-Human protein interaction network, using the experimentally validated SARS-CoV-Human protein interactions. Initially, level-1 and level-2 human spreader proteins are identified in SARS-CoV-Human interaction network, using Susceptible-Infected-Susceptible (SIS) model. These proteins are considered as potential human targets for nCoV bait proteins. A gene-ontology based fuzzy affinity function has been used to construct the nCoV-Human protein interaction network at 99.98% specificity threshold. This also identifies the level-1 human spreaders for COVID-19 in human protein-interaction network. Level-2 human spreaders are subsequently identified using the SIS model. The derived host-pathogen interaction network is finally validated using 7 potential FDA listed drugs for COVID-19 with significant overlap between the known drug target proteins and the identified spreader proteins.

Explainable machine learning and artificial intelligence models have been used to justify a model's decision-making process. This added transparency aims to help improve user performance and understanding of the underlying model. However, in practice, explainable systems face many open questions and challenges. Specifically, designers might reduce the complexity of deep learning models in order to provide interpretability. The explanations generated by these simplified models, however, might not accurately justify and be truthful to the model. This can further add confusion to the users as they might not find the explanations meaningful with respect to the model predictions. Understanding how these explanations affect user behavior is an ongoing challenge. In this paper, we explore how explanation veracity affects user performance and agreement in intelligent systems. Through a controlled user study with an explainable activity recognition system, we compare variations in explanation veracity for a video review and querying task. The results suggest that low veracity explanations significantly decrease user performance and agreement compared to both accurate explanations and a system without explanations. These findings demonstrate the importance of accurate and understandable explanations and caution that poor explanations can sometimes be worse than no explanations with respect to their effect on user performance and reliance on an AI system.

Moovit, an 8-year-old company based in Israel, makes an app that compiles data from public transit systems, ride-hailing services and other resources to help its 800 million users plan the best ways to get around. Intel plans to combine Moovit with Mobileye, a self-driving car specialist that Intel bought for about $15 billion in 2017.

A Google-developed AI that was capable of identifying cases of diabetic retinopathy (DR) with 90 percent accuracy in the testing laboratory has turned out to be much less useful in clinics and hospitals. In laboratory settings, the AI designed by Google Health performed at the equivalent level of a medical'specialist,' but in testing at 11 clinics in Thailand between November 2018 and August 2019, it was substantially less effective. The main challenge for researchers was the quality of images being fed to Google's AI, with 21 percent of the 1,838 photographs taken of patients graded as too low in quality to be processed because of inadequate lighting or unreliable photographic ability of the local clinic workers. Another challenge was slow internet speeds, which made the process of uploading and processing images time consuming. One clinic worker estimating they could only screen around 10 patients in a two hour window, according to a report in Newsweek.

Coronavirus patients with mild symptoms are quarantined at hotels in Tokyo staffed by robots. Five hotels are around the city are using robots to help limit the spread, one being the world's first social humanoid Pepper. 'Please, wear a mask inside,' it says in a perky voice to welcome those moving into the hotel and also offers words of support - 'I hope you recover as quickly as possible.' Other facilities have employed AI-powered robots that disinfect surfaces to limit the need of human workers who are at risk of being exposed. Coronavirus patients with mild symptoms are quarantined at hotels in Tokyo staffed by robots.

Today, Intel announced that it has acquired the transit app developer Moovit for nearly roughly $900 million, confirming rumors that circulated over the weekend. Used by more than 800 million users and services in over 3,000 cities and 102 countries, Moovit combines info from public transit operators and its user community to provide real-time trip mapping and planning services. The deal should help Intel's Mobileye provide new and improved mobility services, like robotaxis. "Moovit is a strong brand trusted by hundreds of millions of people globally. Together, with Mobileye's extensive capabilities in mapping and self-driving technology, we will be able to accelerate our timeline to transform the future of mobility," said Mobileye CEO Amnon Shashua. Intel acquired Israel-based Mobileye in 2017 for $15.3 billion, and today, Mobileye is used in 300 car models by 25 automakers.