Patience is a virtue, depending on a liquid's internal friction. The rate of liquid draining depends a lot on its viscosity and internal friction. Breakthroughs, discoveries, and DIY tips sent six days a week. How much of your life is spent waiting for the last drops of syrup, olive oil, or even bodywash to drip from a container? This routine test of patience is owed entirely to complex fluid dynamics .

Knowledge distillation provides an effective method for deploying complex machine learning models in resource-constrained environments. It typically involves training a smaller student model to emulate either the probabilistic outputs or the internal feature representations of a larger teacher model. By doing so, the student model often achieves substantially better performance on a downstream task compared to when it is trained independently. Nevertheless, the teacher's internal representations can also encode noise or additional information that may not be relevant to the downstream task. This observation motivates our primary question: What are the information-theoretic limits of knowledge transfer? To this end, we leverage a body of work in information theory called Partial Information Decomposition (PID) to quantify the distillable and distilled knowledge of a teacher's representation corresponding to a given student and a downstream task. Moreover, we demonstrate that this metric can be practically used in distillation to address challenges caused by the complexity gap between the teacher and the student representations.

Artificial intelligence (AI) has become indispensable for managing and processing the vast amounts of data generated during the COVID-19 pandemic. Ontology, which formalizes knowledge within a domain using standardized vocabularies and relationships, plays a crucial role in AI by enabling automated reasoning, data integration, semantic interoperability, and extracting meaningful insights from extensive datasets. The diversity of COVID-19 datasets poses challenges in comprehending this information for both human and machines. Existing COVID-19 ontologies are designed to address specific aspects of the pandemic but lack comprehensive coverage across all essential dimensions. To address this gap, CODO, an integrated ontological model has been developed encompassing critical facets of COVID-19 information such as aetiology, epidemiology, transmission, pathogenesis, diagnosis, prevention, genomics, therapeutic safety, and more. This paper reviews CODO since its inception in 2020, detailing its developments and highlighting CODO as a tool for the aggregation, representation, analysis, and visualization of diverse COVID-19 data. The major contribution of this paper is to provide a summary of the development of CODO, and outline the overall development and evaluation approach. By adhering to best practices and leveraging W3C standards, CODO ensures data integration and semantic interoperability, supporting effective navigation of COVID-19 complexities across various domains.

Uncertainty quantification and robustness to distribution shifts are important goals in machine learning and artificial intelligence. Although Bayesian Neural Networks (BNNs) allow for uncertainty in the predictions to be assessed, different sources of uncertainty are indistinguishable. We present Imprecise Bayesian Neural Networks (IBNNs); they generalize and overcome some of the drawbacks of standard BNNs. These latter are trained using a single prior and likelihood distributions, whereas IBNNs are trained using credal prior and likelihood sets. They allow to distinguish between aleatoric and epistemic uncertainties, and to quantify them. In addition, IBNNs are more robust than BNNs to prior and likelihood misspecification, and to distribution shift. They can also be used to compute sets of outcomes that enjoy probabilistic guarantees. We apply IBNNs to two case studies. One, for motion prediction in autonomous driving scenarios, and two, to model blood glucose and insulin dynamics for artificial pancreas control. We show that IBNNs performs better when compared to an ensemble of BNNs benchmark.

Information collection is an important application of multi-robot systems especially in environments that are difficult to operate for humans. The objective of the robots is to maximize information collection from the environment while remaining in their path-length budgets. In this paper, we propose a novel multi-robot information collection algorithm that uses a continuous region partitioning approach to efficiently divide an unknown environment among the robots based on the discovered obstacles in the area, for better load-balancing. Our algorithm gracefully handles situations when some of the robots cannot communicate with other robots due to limited communication ranges.

In this paper, we study the problem of forming coalitions with heterogeneous agents for allocating them to tasks. Several agents work together to complete a given task. Due to the inherent complexity of real-world tasks and limited capabilities of a particular type of a physical agent such as a robot, it is imperative to form a team consisting of different types of robots to complete the tasks. Our work in this paper proposes a distributed bipartite graph partitioning approach along with a region growing strategy for coalition formation with heterogeneous agents such as humans and/or robots for instantaneous allocation to tasks (ST-MR-IA). We also extend this approach to apply in the scenarios where the tasks might have dependencies among each other (ST-MR-TD).We have implemented the proposed algorithms within theWebots simulator. The proposed strategy allocates near-optimal (up to 98%) agent coalitions to tasks. Results also show that our proposed approach can easily handle as many as 100 agents and 10 tasks while spending an almost negligible amount of time.

For individuals with anxiety disorders, maladaptive feelings and negative beliefs can interfere with daily activities and importantly, social relationships. Literature has examined both direct and indirect influences of an individual's anxiety on their social interactions, however, how they co-vary temporally remains less explored. As individuals appropriate social media platforms more pervasively, can anxiety play an equally significant role in impacting one's \textit{online} social interactions? This paper seeks to answer this question. Employing a dataset of 200 Twitter users, their timeline, and social network data, we examine the relationship between manifested anxiety and various attributes of social interaction of a user by employing Granger causality and time series forecasting approaches. We observe that increases in anxiety levels of an individual result in increased future interaction with weak ties, indicating a tendency to seek support from the broader online community. We discuss how our findings provide novel insights and practical lessons around the impact of an individual's mental health state on their online social interactions.

The major objective of this work is to study and report the existing ontology-driven models for narrative information. The paper aims to analyze these models across various domains. The goal of this work is to bring the relevant literature, and ontology models under one umbrella, and perform a parametric comparative study. A systematic literature review methodology was adopted for an extensive literature selection. A random stratified sampling technique was used to select the models from the literature. The findings explicate a comparative view of the narrative models across domains. The differences and similarities of knowledge representation across domains, in case of narrative information models based on ontology was identified. There are significantly fewer studies that reviewed the ontology-based narrative models. This work goes a step further by evaluating the ontologies using the parameters from narrative components. This paper will explore the basic concepts and top-level concepts in the models. Besides, this study provides a comprehensive study of the narrative theories in the context of ongoing research. The findings of this work demonstrate the similarities and differences among the elements of the ontology across domains. It also identifies the state of the art literature for ontology-based narrative information.

Metadata vocabularies are used in various domains of study. It provides an in-depth description of the resources. In this work, we develop Algorithm Metadata Vocabulary (AMV), a vocabulary for capturing and storing the metadata about the algorithms (a procedure or a set of rules that is followed step-by-step to solve a problem, especially by a computer). The snag faced by the researchers in the current time is the failure of getting relevant results when searching for algorithms in any search engine. AMV is represented as a semantic model and produced OWL file, which can be directly used by anyone interested to create and publish algorithm metadata as a knowledge graph, or to provide metadata service through SPARQL endpoint. To design the vocabulary, we propose a well-defined methodology, which considers real issues faced by the algorithm users and the practitioners. The evaluation shows a promising result.

"Digital transformation since the pandemic has been massive. Telehealth has gone from being a novelty to a necessity. Having said that, we need to be reliant on healthcare institutions to get cured and we need technology to make it better," said Mitali Dutta, head of data science and predictive analysis, group IT information and data management, Philips Innovation Campus, at her session at The Rising 2021 by Analytics India Magazine. She pointed at a rise in chronic diseases and healthcare costs, a scarcity of healthcare professionals in India. According to Dutta, the healthcare industry has to focus on the following four aspects, which she called Quadruple AIM of India's healthcare system: To achieve all the above, India needs artificial intelligence.