In machine learning, the ability to assess uncertainty in model predictions is crucial for decision-making, safety-critical applications, and model generalizability. This work introduces a novel approach for epistemic uncertainty estimation for ensemble models using pairwise-distance estimators (PaiDEs). These estimators utilize the pairwise-distance between model components to establish bounds on entropy, which are then used as estimates for information-based criterion. Unlike recent deep learning methods for epistemic uncertainty estimation, which rely on sample-based Monte Carlo estimators, PaiDEs are able to estimate epistemic uncertainty up to 100 times faster, over a larger input space (up to 100 times) and perform more accurately in higher dimensions. To validate our approach, we conducted a series of experiments commonly used to evaluate epistemic uncertainty estimation: 1D sinusoidal data, $\textit{Pendulum-v0}$, $\textit{Hopper-v2}$, $\textit{Ant-v2}$ and $\textit{Humanoid-v2}$. For each experimental setting, an Active Learning framework was applied to demonstrate the advantages of PaiDEs for epistemic uncertainty estimation.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Delaware's low elevation mixed with crowded beaches and limited exit routes make the state particularly vulnerable to massive flooding, but officials hope an influx of federal infrastructure money will trigger future evacuation plans automatically via artificial intelligence. The Biden administration was set to announce a total of $53 million in grants Thursday to Delaware and seven other states aimed at high-tech solutions to traffic congestion problems. Although the money comes from the infrastructure law the president signed in 2021, many of the programs -- including the $5 million for flood response efforts in Biden's home state -- have evolved since then. "What's new is the predictive analysis; the machine learning," U.S. Federal Highway Administrator Shailen Bhatt, Delaware's former transportation secretary, said in an interview with The Associated Press.

The ultimate goal, he said, is to validate and train AI algorithms on large amounts of data, while reducing privacy issues surrounding personal medical information. "More and more…synthetic data is going to overtake and be the way people do AI in the future," Mr. Bhatt said. Anthem, which has been using Amazon.com Inc.'s Amazon Web Services as a cloud provider since 2017, tapped Google Cloud last year for its data analytics and AI capabilities as part of an ongoing effort to become more customer-centric and focus on members' entire healthcare journeys, Mr. Bhatt said. It's a continuing effort that includes Anthem's work with synthetic data. This week, Anthem's shareholders are voting on a proposed rebranding of the company to Elevance Health as part of that same effort.

We present a cognitive design assistance system equipped with analytical capabilities aimed at anticipating architectural building design performance with respect to people-centred functional design goals. The paper focuses on the system capability to generate "narratives of visuo-locomotive user experience" from digital computer-aided architecture design (CAAD) models. The system is based on an underlying declarative narrative representation and computation framework pertaining to conceptual, geometric, and qualitative spatial knowledge. The semantics of the declarative narrative model, i.e., the overall representation and computation model, is founded on: (a).

We demonstrate the need and potential of systematically integrated vision and semantics solutions for visual sensemaking in the backdrop of autonomous driving. A general neurosymbolic method for online visual sensemaking using answer set programming (ASP) is systematically formalised and fully implemented. The method integrates state of the art in visual computing, and is developed as a modular framework that is generally usable within hybrid architectures for realtime perception and control. We evaluate and demonstrate with community established benchmarks KITTIMOD, MOT-2017, and MOT-2020. As use-case, we focus on the significance of human-centred visual sensemaking -- e.g., involving semantic representation and explainability, question-answering, commonsense interpolation -- in safety-critical autonomous driving situations. The developed neurosymbolic framework is domain-independent, with the case of autonomous driving designed to serve as an exemplar for online visual sensemaking in diverse cognitive interaction settings in the backdrop of select human-centred AI technology design considerations. Keywords: Cognitive Vision, Deep Semantics, Declarative Spatial Reasoning, Knowledge Representation and Reasoning, Commonsense Reasoning, Visual Abduction, Answer Set Programming, Autonomous Driving, Human-Centred Computing and Design, Standardisation in Driving Technology, Spatial Cognition and AI.

Because the plug isn't reversible, connecting a USB device to a computer can often be a frustrating experience. Because the plug isn't reversible, connecting a USB device to a computer can often be a frustrating experience. Your files are done syncing, and you go to plug in your thumb drive. Humiliated and discouraged, you flip it and try again. How could this be possible?

When you post something on LinkedIn, chances are that an algorithm made by Rushi Bhatt's team in Bengaluru has checked if it's kosher to be on the professional network. It sounds easy but consider the complexity: LinkedIn has over 560 million members, 20 million companies, millions of job postings and it works in 24 different languages. If all its millions of users seamlessly post on the platform every day, it is because LinkedIn's algorithms, with a lot of help from humans, green-light them before the user can blink an eye. "We have to walk this fine line between freedom of expression and not letting poor content live on the site. That makes it really complicated for everybody, including humans," says Bhatt, an alum of Amazon and Yahoo with a Ph.D. in cognitive and neural systems from Boston University and degrees from the Tata Institute of Fundamental Research and what is today NIT, Surat. At its worst, a poor newsfeed can drive away users. On the other hand, a good one can keep you hooked on a platform for hours. At LinkedIn, it is the job of the "Feed AI" team to maintain fidelity. Bhatt's job is to literally keep the NSFW stuff away. It's a problem almost all major platforms with user-generated content – be it Youtube or Twitter – struggle with.

Boon of technology has changed the human civilization for good, as constant evolution in technology being intensively tracked and leveraged by new-age entrepreneurs, it only becomes imminent that aspects such as the Internet-of-Things (IoT), artificial Intelligence (AI), Machine Learning (ML), Deep Learning and more; are utilised by entrepreneurs to develop technology-driven models to actually solve societal problems. In this regard, with futuristic technology penetration being the focal point; Entrepreneur India lists the relevance of a domain called Machine Learning for entrepreneurs in 2018 to harness and develop solutions such that societal problems are mitigated whilst driving recognition for developing unconventional solutions. "Machine Learning has the potential to help create a utopian world without any disease, crime, and poverty," states Yogesh Bhatt who is Vice President at Bengaluru-based Manipal Prolearn; a unit of Manipal Global Education Services. This is substantiated when we consider the fact that data scientists today have been working at the heart of societal issues in domains healthcare and medicine; which are undoubtedly in a definite need for disruption. Specifically, Machine Learning is now driving doctors through predictive analytics; towards aspects such as enhancing the success rates when it comes to diagnosing and treating life threatening ailments such as clinical depression and cancer. These aspects potentially provide exciting prospects for entrepreneurs, to come up with models driven by ML, as there practically (not theoretically) exists opportunity for impact to introduce positive changes in the lives of people.

We present ASP Modulo `Space-Time', a declarative representational and computational framework to perform commonsense reasoning about regions with both spatial and temporal components. Supported are capabilities for mixed qualitative-quantitative reasoning, consistency checking, and inferring compositions of space-time relations; these capabilities combine and synergise for applications in a range of AI application areas where the processing and interpretation of spatio-temporal data is crucial. The framework and resulting system is the only general KR-based method for declaratively reasoning about the dynamics of `space-time' regions as first-class objects. We present an empirical evaluation (with scalability and robustness results), and include diverse application examples involving interpretation and control tasks.

We propose a hybrid architecture for systematically computing robust visual explanation(s) encompassing hypothesis formation, belief revision, and default reasoning with video data. The architecture consists of two tightly integrated synergistic components: (1) (functional) answer set programming based abductive reasoning with space-time tracklets as native entities; and (2) a visual processing pipeline for detection based object tracking and motion analysis. We present the formal framework, its general implementation as a (declarative) method in answer set programming, and an example application and evaluation based on two diverse video datasets: the MOTChallenge benchmark developed by the vision community, and a recently developed Movie Dataset.