Large-scale knowledge graphs (KGs) provide structured representations of human knowledge. However, as it is impossible to contain all knowledge, KGs are usually incomplete. Reasoning based on existing facts paves a way to discover missing facts. In this paper, we study the problem of learning logic rules for reasoning on knowledge graphs for completing missing factual triplets. Learning logic rules equips a model with strong interpretability as well as the ability to generalize to similar tasks. We propose a model called MPLR that improves the existing models to fully use training data and multi-target scenarios are considered. In addition, considering the deficiency in evaluating the performance of models and the quality of mined rules, we further propose two novel indicators to help with the problem. Experimental results empirically demonstrate that our MPLR model outperforms state-of-the-art methods on five benchmark datasets. The results also prove the effectiveness of the indicators.

In any debate, there are always at least two sides. That reasoning also applies to whether or not it is a good idea to use artificial intelligence technology to try stemming the advantages of cybercriminals who are already using AI to improve their success ratio. In an email exchange, I asked Ramprakash Ramamoorthy, director of research at ManageEngine, a division of Zoho Corporation, for his thoughts on the matter. Ramamoorthy is firmly on the affirmative side for using AI to fight cybercrime. He said, "The only way to combat cybercriminals using AI-enhanced attacks is to fight fire with fire and employ AI countermeasures."

Recent advances in Computer Vision and Machine Learning empowered the use of image and positional data in several high-level analyses in Sports Science, such as player action classification, recognition of complex human movements, and tactical analysis of team sports. In the context of sports action analysis, the use of positional data allows new developments and opportunities by taking into account players' positions over time. Exploiting the positional data and its sequence in a systematic way, we proposed a framework that bridges association rule mining and action recognition. The proposed Sports Action Mining (SAM) framework is grounded on the usage of positional data for recognising actions, e.g., dribbling. We hypothesise that different sports actions could be modelled using a sequence of confidence levels computed from previous players' locations.

Decision sets and decision lists are two of the most easily explainable machine learning models. Given the renewed emphasis on explainable machine learning decisions, both of these machine learning models are becoming increasingly attractive, as they combine small size and clear explainability. In this paper, we define size as the total number of literals in the SAT encoding of these rule-based models as opposed to earlier work that concentrates on the number of rules. In this paper, we develop approaches to computing minimum-size "perfect" decision sets and decision lists, which are perfectly accurate on the training data, and minimal in size, making use of modern SAT solving technology. We also provide a new method for determining optimal sparse alternatives, which trade off size and accuracy. The experiments in this paper demonstrate that the optimal decision sets computed by the SAT-based approach are comparable with the best heuristic methods, but much more succinct, and thus, more explainable. We contrast the size and test accuracy of optimal decisions lists versus optimal decision sets, as well as other state-of-the-art methods for determining optimal decision lists. Finally, we examine the size of average explanations generated by decision sets and decision lists.

In this paper, we present a method of building strong, explainable classifiers in the form of Boolean search rules. We developed an interactive environment called CASE (Computer Assisted Semantic Exploration) which exploits word co-occurrence to guide human annotators in selection of relevant search terms. The system seamlessly facilitates iterative evaluation and improvement of the classification rules. The process enables the human annotators to leverage the benefits of statistical information while incorporating their expert intuition into the creation of such rules. We evaluate classifiers created with our CASE system on 4 datasets, and compare the results to machine learning methods, including SKOPE rules, Random forest, Support Vector Machine, and fastText classifiers. The results drive the discussion on trade-offs between superior compactness, simplicity, and intuitiveness of the Boolean search rules versus the better performance of state-of-the-art machine learning models for text classification.

Though deep reinforcement learning agents have achieved unprecedented success in recent years, their learned policies can be brittle, failing to generalize to even slight modifications of their environments or unfamiliar situations. The black-box nature of the neural network learning dynamics makes it impossible to audit trained deep agents and recover from such failures. In this paper, we propose a novel representation and learning approach to capture environment dynamics without using neural networks. It originates from the observation that, in games designed for people, the effect of an action can often be perceived in the form of local changes in consecutive visual observations. Our algorithm is designed to extract such vision-based changes and condense them into a set of action-dependent descriptive rules, which we call ''visual rewrite rules'' (VRRs). We also present preliminary results from a VRR agent that can explore, expand its rule set, and solve a game via planning with its learned VRR world model. In several classical games, our non-deep agent demonstrates superior performance, extreme sample efficiency, and robust generalization ability compared with several mainstream deep agents.

In "Hyping Artificial Intelligence Hinders Innovation" (podcast episode 163), Andrew McDiarmid interviewed Erik J. Larson, author of The Myth of Artificial Intelligence: Why Computers Can't Think the Way We Do (2021) (Harvard University Press, 2021) on the way "Machines will RULE!" Erik Larson has founded two two DARPA-funded artificial intelligence startups. Inthe book he urges us to go back to the drawing board with AI research and development. This portion begins at 01:59 min. A partial transcript and notes, Show Notes, and Additional Resources follow.

A cognitive architecture aimed at cumulative learning must provide the necessary information and control structures to allow agents to learn incrementally and autonomously from their experience. This involves managing an agent's goals as well as continuously relating sensory information to these in its perception-cognition information stack. The more varied the environment of a learning agent is, the more general and flexible must be these mechanisms to handle a wider variety of relevant patterns, tasks, and goal structures. While many researchers agree that information at different levels of abstraction likely differs in its makeup and structure and processing mechanisms, agreement on the particulars of such differences is not generally shared in the research community. A binary processing architecture (often referred to as System-1 and System-2) has been proposed as a model of cognitive processing for low- and high-level information, respectively. We posit that cognition is not binary in this way and that knowledge at any level of abstraction involves what we refer to as neurosymbolic information, meaning that data at both high and low levels must contain both symbolic and subsymbolic information. Further, we argue that the main differentiating factor between the processing of high and low levels of data abstraction can be largely attributed to the nature of the involved attention mechanisms. We describe the key arguments behind this view and review relevant evidence from the literature.

The transition to information-based healthcare delivery and administration has been expedited by technological advancements. AI/ML-driven information systems are critical to today's multidisciplinary approach to improving healthcare outcomes, which includes sophisticated imaging and genetic-based tailored therapy models. Artificial Intelligence is basically a great evolution in the field of computer science. AI has changed the way of computing and carrying out tasks easier as well as automated. Artificial Intelligence is a way in which a machine learns about patterns and ways and by using its intelligence produces desired results.

Money laundering and other types of financial crime have plagued the financial industry for years. Banks and other financial institutions have consistently found themselves one step behind criminals looking to take advantage of the holes within banks' security and monitoring systems and carry out criminal activity undetected. In response, many of these organizations have put in place anti-money laundering (AML) solutions. However, it's no secret that these systems still leave much to be desired. Attempting to stop money laundering without concern for accuracy can create real challenges.