This paper presents a method for semantic indexing and describes its application in the field of knowledge representation. Starting point of the semantic indexing is the knowledge represented by concept hierarchies. The goal is to assign keys to nodes (concepts) that are hierarchically ordered and syntactically and semantically correct. With the indexing algorithm, keys are computed such that concepts are partially unifiable with all more specific concepts and only semantically correct concepts are allowed to be added. The keys represent terminological relationships. Correctness and completeness of the underlying indexing algorithm are proven. The use of classical relational databases for the storage of instances is described. Because of the uniform representation, inference can be done using case-based reasoning and generic problem solving methods.

Many real world tasks require multiple agents to work together. Multi-agent reinforcement learning (RL) methods have been proposed in recent years to solve these tasks, but current methods often fail to efficiently learn policies. We thus investigate the presence of a common weakness in single-agent RL, namely value function overestimation bias, in the multi-agent setting. Based on our findings, we propose an approach that reduces this bias by using double centralized critics. We evaluate it on six mixed cooperative-competitive tasks, showing a significant advantage over current methods. Finally, we investigate the application of multi-agent methods to high-dimensional robotic tasks and show that our approach can be used to learn decentralized policies in this domain.

The ability to reason about temporal and causal events from videos lies at the core of human intelligence. Most video reasoning benchmarks, however, focus on pattern recognition from complex visual and language input, instead of on causal structure. We study the complementary problem, exploring the temporal and causal structures behind videos of objects with simple visual appearance. To this end, we introduce the CoLlision Events for Video REpresentation and Reasoning (CLEVRER), a diagnostic video dataset for systematic evaluation of computational models on a wide range of reasoning tasks. Motivated by the theory of human casual judgment, CLEVRER includes four types of questions: descriptive (e.g., "what color"), explanatory ("what is responsible for"), predictive ("what will happen next"), and counterfactual ("what if"). We evaluate various state-of-the-art models for visual reasoning on our benchmark. While these models thrive on the perception-based task (descriptive), they perform poorly on the causal tasks (explanatory, predictive and counterfactual), suggesting that a principled approach for causal reasoning should incorporate the capability of both perceiving complex visual and language inputs, and understanding the underlying dynamics and causal relations. We also study an oracle model that explicitly combines these components via symbolic representations.

The CP 2002 paper entitled "Breaking Row and Column Symmetries in Matrix Models" by Flener et al. [6] describes some of the first work for identifying and analyzing row and column symmetry in mat rix models and for efficiently and effectively dealing with such symmetry u sing static symmetry-breaking ordering constraints. This commentary provides a retrospective on that work and highlights some of the subsequent work on the topic.

While AI techniques have found many successful applications in autonomous systems, many of them permit behaviours that are difficult to interpret and may lead to uncertain results. We follow the "verification as planning" paradigm and propose to use model checking techniques to solve planning and goal reasoning problems for autonomous systems. We give a new formulation of Goal Task Network (GTN) that is tailored for our model checking based framework. We then provide a systematic method that models GTNs in the model checker Process Analysis Toolkit (PAT). We present our planning and goal reasoning system as a framework called Goal Reasoning And Verification for Independent Trusted Autonomous Systems (GRAVITAS) and discuss how it helps provide trustworthy plans in an uncertain environment. Finally, we demonstrate the proposed ideas in an experiment that simulates a survey mission performed by the REMUS-100 autonomous underwater vehicle.

"Deepfake" techniques today are capable of producing artificial intelligence-generated videos of real people doing fictional things or fictional people doing real things. Their applications are being invented along the way ever since the success of GANs. The deep learning community is still partially clueless about the outcomes of the existing malicious content. That is why, industry experts have been collaborating to create awareness amongst the community. As a machine learning practitioner, one can do their own part by availing the resources on deep fake.

The entrance of the world into the digital age has overhauled almost all the aspects of life, out of which one of the most noticeable evolution is – 'the Smart Homes of New Age'. Automation, which is termed as a method, technique, or arrangement of operating or controlling a procedure by electronic gadgets and reducing human interference to a minimum, has risen as a new industry vertical in the last two decades. Gone are the days when someone has to check the house twice before leaving so that no lights, fans, or appliances are left switched on. It's the age of automation, where relay modules, sensors, and automated systems will take care of the optimal usage of electricity and all devices. Moreover, the past years have witnessed AI evolving as a technology for developing automatic systems and making decisions using case-based reasoning.

A recent report by ProPublica showed that medical imaging data of over 5 million patients in the United States are publicly available on the internet. As a result of 187 misconfigured servers, medical imaging data, often containing identifiable patient information that should be protected, is "sitting unprotected on the internet and available to anyone with basic computer expertise." Researchers discovered over 13.7 million medical tests, including 400,000 with downloadable images. These imaging records were stored on servers, including systems used for archiving medical images, without a robust solution in place to monitor for unauthorized changes or to ensure the servers were securely configured and in compliance with regulatory standards. These medical images include MRI, X-Rays and accompanying identifiable patient data that could be used for blackmail.

Artificial intelligence based on medical claims data outperforms traditional models in stratifying patient risk. ABSTRACT Objectives: Current models for patient risk prediction rely on practitioner expertise and domain knowledge. This study presents a deep learning model--a type of machine learning that does not require human inputs--to analyze complex clinical and financial data for population risk stratification. Methods: "Skip-Gram," an unsupervised deep learning approach that uses neural networks for prediction modeling, used data from 2014 and 2015 to predict the risk of hospitalization in 2016. The area under the curve (AUC) of the deep learning model was compared with that of both the Clinical Classifications Software and the commercial DxCG Intelligence predictive risk models, each with and without demographic and utilization features.

Natural language processing (NLP) -- the AI subfield dealing with machine reading comprehension -- isn't by any stretch solved, and that's because syntactic nuances can enormously impact the meaning of a sentence or phrase. Consider the paraphrase pairs "Flights from New York to Florida" and "Flights to Florida from New York," which convey the same thing. Even state-of-the-art algorithms fail to distinguish them from a snippet like "Flights from Florida to New York," which has a different meaning. Google thinks a greater diversity of data is one of the keys to solving hard NLP problems, and to this end, it's today releasing two new corpora: Paraphrase Adversaries from Word Scrambling (PAWS) in English. Both data sets contain "well-formed" pairs of paraphrases and non-paraphrases, which Google says can improve algorithmic accuracy in capturing word order and structure from below 50% to between 85% and 89%.