Regret has been established as a foundational concept in online learning, and likewise has important applications in the analysis of learning dynamics in games. Regret quantifies the difference between a learner’s performance against a baseline in hindsight. It is well known that regret-minimizing algorithms converge to certain classes of equilibria in games; however, traditional forms of regret used in game theory predominantly consider baselines that permit deviations to deterministic actions or strategies. In this paper, we revisit our understanding of regret from the perspective of deviations over partitions of the full mixed strategy space (i.e., probability distributions over pure strategies), under the lens of the previously-established Φ-regret framework, which provides a continuum of stronger regret measures. Importantly, Φ-regret enables learning agents to consider deviations from and to mixed strategies, generalizing several existing notions of regret such as external, internal, and swap regret, and thus broadening the insights gained from regret-based analysis of learning algorithms. We prove here that the well-studied evolutionary learning algorithm of replicator dynamics (RD) seamlessly minimizes the strongest possible form of Φ-regret in generic 2 × 2 games, without any modification of the underlying algorithm itself. We subsequently conduct experiments validating our theoretical results in a suite of 144 2 × 2 games wherein RD exhibits a diverse set of behaviors. We conclude by providing empirical evidence of Φ-regret minimization by RD in some larger games, hinting at further opportunity for Φ-regret based study of such algorithms from both a theoretical and empirical perspective.

Ottawa, Canada, June 2017: Carlton University's Department of Mechanical and Aerospace Engineering announced the development of a technology that would revolutionise the future of space travel. As man goes ever further in his attempts to colonise space, technology is being developed – as mentioned – through which a 3D printer can self-replicate using materials collected on the surface of a specific celestial body. According to Japanese-born astrophysicist Michio Kaku – a summa cum laude graduate of Harvard University: "Man is led to believe that, in order to explore the stars, you need a huge spaceship, but this is not the case. However – apart from the help of warp drive and wormholes (faster-than light travels according to the Einstein-Rosen bridge theory) – at that juncture, instead of spaceships full of humans, could not the universe be explored and populated with probes like von Neumann's? Exploration scientists have been working for decades on the project of turning mankind into mechanical or transhuman beings in order to create an entire cloned race of robots. Transhumanism is a philosophical and intellectual movement that advocates improving the human condition by developing and making widely available sophisticated technologies that can greatly enhance longevity and cognition. Ottawa, Canada, June 2017: Carlton University's Department of Mechanical and Aerospace Engineering announced the development of a technology that would revolutionise the future of space travel. As man goes ever further in his attempts to colonise space, technology is being developed – as mentioned – through which a 3D printer can self-replicate using materials collected on the surface of a specific celestial body. According to Japanese-born astrophysicist Michio Kaku – a summa cum laude graduate of Harvard University: "Man is led to believe that, in order to explore the stars, you need a huge spaceship, but this is not the case.

Researchers have developed a process using Machine Learning (ML) methods to find rock art in remote, hard-to-access areas of Australia. The study, co-led by Dr. Andrea Jalandoni, a digital archaeologist from Griffith University's Center for Social and Cultural Research, was published in the Aug. 2022 issue of the Journal of Archaeological Science. In the study, university researchers trained a ML model to detect whether painted rock art was present in an image by feeding it hundreds of images of rock art found in Kakadu National Park. The model achieved an impressive 89% success rate. Dr. Jalandoni told the Australian Associated Press, "Our machine learning model picks up whether an area photographed potentially contains previously undiscovered rock art, scientists can then go in and verify if there is rock art present and do more research."

We introduce a new algorithm, Regression based Supervised Learning (RSL), for learning per instance Neural Network (NN) defined heuristic functions for classical planning problems. RSL uses regression to select relevant sets of states at a range of different distances from the goal. RSL then formulates a Supervised Learning problem to obtain the parameters that define the NN heuristic, using the selected states labeled with exact or estimated distances to goal states. Our experimental study shows that RSL outperforms, in terms of coverage, previous classical planning NN heuristics functions while requiring two orders of magnitude less training time.

Neural networks have had discernible achievements in a wide range of applications. The wide-spread adoption also raises the concern of their dependability and reliability. Similar to traditional decision-making programs, neural networks can have defects that need to be repaired. The defects may cause unsafe behaviors, raise security concerns or unjust societal impacts. In this work, we address the problem of repairing a neural network for desirable properties such as fairness and the absence of backdoor. The goal is to construct a neural network that satisfies the property by (minimally) adjusting the given neural network's parameters (i.e., weights). Specifically, we propose CARE (\textbf{CA}usality-based \textbf{RE}pair), a causality-based neural network repair technique that 1) performs causality-based fault localization to identify the `guilty' neurons and 2) optimizes the parameters of the identified neurons to reduce the misbehavior. We have empirically evaluated CARE on various tasks such as backdoor removal, neural network repair for fairness and safety properties. Our experiment results show that CARE is able to repair all neural networks efficiently and effectively. For fairness repair tasks, CARE successfully improves fairness by $61.91\%$ on average. For backdoor removal tasks, CARE reduces the attack success rate from over $98\%$ to less than $1\%$. For safety property repair tasks, CARE reduces the property violation rate to less than $1\%$. Results also show that thanks to the causality-based fault localization, CARE's repair focuses on the misbehavior and preserves the accuracy of the neural networks.

Few-shot recognition involves training an image classifier to distinguish novel concepts at test time using few examples (shot). Existing approaches generally assume that the shot number at test time is known in advance. This is not realistic, and the performance of a popular and foundational method has been shown to suffer when train and test shots do not match. We conduct a systematic empirical study of this phenomenon. In line with prior work, we find that shot sensitivity is broadly present across metric-based few-shot learners, but in contrast to prior work, larger neural architectures provide a degree of built-in robustness to varying test shot. More importantly, a simple, previously known but greatly overlooked class of approaches based on cosine distance consistently and greatly improves robustness to shot variation, by removing sensitivity to sample noise. We derive cosine alternatives to popular and recent few-shot classifiers, broadening their applicability to realistic settings. These cosine models consistently improve shot-robustness, outperform prior shot-robust state of the art, and provide competitive accuracy on a range of benchmarks and architectures, including notable gains in the very-low-shot regime.

Mental health disorders may cause severe consequences on all the countries' economies and health. For example, the impacts of the COVID-19 pandemic, such as isolation and travel ban, can make us feel depressed. Identifying early signs of mental health disorders is vital. For example, depression may increase an individual's risk of suicide. The state-of-the-art research in identifying mental disorder patterns from textual data, uses hand-labelled training sets, especially when a domain expert's knowledge is required to analyse various symptoms. This task could be time-consuming and expensive. To address this challenge, in this paper, we study and analyse the various clinical and non-clinical approaches to identifying mental health disorders. We leverage the domain knowledge and expertise in cognitive science to build a domain-specific Knowledge Base (KB) for the mental health disorder concepts and patterns. We present a weaker form of supervision by facilitating the generating of training data from a domain-specific Knowledge Base (KB). We adopt a typical scenario for analysing social media to identify major depressive disorder symptoms from the textual content generated by social users. We use this scenario to evaluate how our knowledge-based approach significantly improves the quality of results.

Explainable artificial intelligence is a research field that tries to provide more transparency for autonomous intelligent systems. Explainability has been used, particularly in reinforcement learning and robotic scenarios, to better understand the robot decision-making process. Previous work, however, has been widely focused on providing technical explanations that can be better understood by AI practitioners than non-expert end-users. In this work, we make use of human-like explanations built from the probability of success to complete the goal that an autonomous robot shows after performing an action. These explanations are intended to be understood by people who have no or very little experience with artificial intelligence methods. This paper presents a user trial to study whether these explanations that focus on the probability an action has of succeeding in its goal constitute a suitable explanation for non-expert end-users. The results obtained show that non-expert participants rate robot explanations that focus on the probability of success higher and with less variance than technical explanations generated from Q-values, and also favor counterfactual explanations over standalone explanations.

The goal of a recommendation system is to model the relevance between each user and each item through the user-item interaction history, so that maximize the positive samples score and minimize negative samples. Currently, two popular loss functions are widely used to optimize recommender systems: the pointwise and the pairwise. Although these loss functions are widely used, however, there are two problems. (1) These traditional loss functions do not fit the goals of recommendation systems adequately and utilize prior knowledge information sufficiently. (2) The slow convergence speed of these traditional loss functions makes the practical application of various recommendation models difficult. To address these issues, we propose a novel loss function named Supervised Personalized Ranking (SPR) Based on Prior Knowledge. The proposed method improves the BPR loss by exploiting the prior knowledge on the interaction history of each user or item in the raw data. Unlike BPR, instead of constructing triples, the proposed SPR constructs quadruples. Although SPR is very simple, it is very effective. Extensive experiments show that our proposed SPR not only achieves better recommendation performance, but also significantly accelerates the convergence speed, resulting in a significant reduction in the required training time.

WNS (Holdings) Limited a leading provider of global Business Process Management (BPM) services, today announced it has acquired Vuram, a global leader in enterprise automation services. Vuram helps companies accelerate digital transformation by aligning, automating, and optimizing processes using a combination of low-code software applications and intelligent automation platforms. By integrating these technologies into core business operations, Vuram is able to drive end-to-end enterprise automation and the creation of custom, scalable BPM solutions. These solutions include the ability to extract, collect, and categorize data using OCR and AI-based document processing, develop rule-based processing engines and ML-based augmentation, and leverage advanced analytics to improve decision-making. Vuram has also created customizable, low-code, "plug and play" solutions across front, middle, and back-office functions, including industry-specific solutions for the Banking/Financial Services, Insurance, and Healthcare verticals.