The Weak Completion Semantics (WCS) is a computational cognitive theory that has shown to be successful in modeling episodes of human reasoning. As the WCS is a recently developed logic programming approach, this paper investigates the correspondence of the WCS with respect to the well-established Answer Set Semantics (ASP). The underlying three-valued logic of both semantics is different and their models are evaluated with respect to different program transformations. We first illustrate these differences by the formal representation of some examples of a well-known psychological experiment, the suppression task. After that, we will provide a translation from logic programs understood under the WCS into logic programs understood under the ASP. In particular, we will show that logic programs under the WCS can be represented as logic programs under the ASP by means of a definition completion, where all defined atoms in a program must be false when their definitions are false.

A prototype for automated reasoning over legal texts, called NAI, is presented. As an input, NAI accepts formalized logical representations of such legal texts that can be created and curated using an integrated annotation interface. The prototype supports automated reasoning over the given text representation and multiple quality assurance procedures. The pragmatics of the NAI suite as well its feasibility in practical applications is studied on a fragment of the Smoking Prohibition (Children in Motor Vehicles) (Scotland) Act 2016 of the Scottish Parliament.

A BSTRACT Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match a state change inside the CPU and RAM. We develop a neural program synthesis algorithm, AutoAssem-blet, learned via self-learning reinforcement learning that explores the large code space efficiently. Policy networks and value networks are learned to reduce the breadth and depth of the Monte Carlo Tree Search, resulting in better synthesis performance. We also propose an effective multi-entropy policy sampling technique to alleviate online update correlations. We apply AutoAssemblet to basic programming tasks and show significant higher success rates compared to several competing baselines. Much progress has been made in the field with the development of methods along the vein of neural program synthesis (Parisotto et al., 2016; Balog et al., 2017; Bunel et al., 2018; Hayati et al., 2018; Desai et al., 2016; Yin & Neubig, 2017; Kant, 2018). Neural program synthesis models build on the top of neural network architectures to synthesize human-readable programs that match desired executions.

This is a quick transcript of the interview of Peter Norvig by Lex Fridman. I find this interview so interesting and revealing, that I decided to take on the task of making a transcript of the interview published in YouTube. Lex Friedman: The following is a conversation with Peter Norvig. A Modern Approach", and educated and inspired a whole generation of researchers, including myself, to get into the field of Artificial Intelligence. This is the Artificial Intelligence podcast. Lex Fridman: Most researchers in the AI community, including myself, own all three editions, red green and blue, of the "Artificial intelligence, a modern approach", the field defining textbook. As many people are aware that you wrote with Stuart Russell, how is the book changed, and how have you changed in relation to it from the first edition to the second, to the third, and now fourth edition as you work on it? Peter Norvig: Yeah so it's been a lot of years, a lot of changes. One of the things changing from the first, to maybe the second, or third, was just the rise of computing power, right? So, I think in the First Edition we said: "here's predicate logic but that only goes so far because pretty soon you have millions of short little medical expressions and they can possibly fit in memory, so we're gonna use first-order logic that's more concise." And then we quickly realized: "Oh, predicate logic is pretty nice because there are really fast Sat solvers, and other things, and look there's only millions of expressions and that fits easily into memory, or maybe even billions fit into memory now.

To celebrate the first 25 years of the International Conference on Principles and Practice of Constraint Programming (CP) the editors invited the authors of the most cited paper of each year to write a commentary on their paper. This report describes our reflections on the CP 2014 paper "Incremental Cardinality Constraints for MaxSAT" and its impact on the Maximum Satisfiability community and beyond.

The article introduces a notion of a stochastic game with failure states and proposes two logical systems with modality "coalition has a strategy to transition to a non-failure state with a given probability while achieving a given goal." The logical properties of this modality depend on whether the modal language allows the empty coalition. The main technical results are a completeness theorem for a logical system with the empty coalition, a strong completeness theorem for the logical system without the empty coalition, and an incompleteness theorem which shows that there is no strongly complete logical system in the language with the empty coalition.1. Introduction In this article we study coalition power in stochastic games. An example of such a game is the road situation depicted in Figure 1. In this situation, self-driving car a is trying to pass self-driving car b . Unexpectedly, a truck moving in the opposite direction appears on the road. For the sake of simplicity, we assume that cars a and b have only three strategies: slowdown (), maintain the current speed (0), and accelerate (). We also assume that the truck is too heavy to significantly change the speed before a possible collision. The diagram in Figure 2 describes probabilities of different outcomes of all possible combinations of actions of cars a and b . This diagram has five states: state p is the current ("passing") state of the system.

A BSTRACT The capability of making interpretable and self-explanatory decisions is essential for developing responsible machine learning systems. In this work, we study the learning to explain problem in the scope of inductive logic programming (ILP). We propose Neural Logic Inductive Learning (NLIL), an efficient differentiable ILP framework that learns first-order logic rules that can explain the patterns in the data. In experiments, compared with the state-of-the-art methods, we find NLIL can search for rules that are x10 times longer while remaining x3 times faster. We also show that NLIL can scale to large image datasets, i.e. The recent years have witnessed the growing success of deep learning models in a wide range of applications. However, these models are also criticized for the lack of interpretability in its behavior and decision making process (Lipton, 2016; Mittelstadt et al., 2019), and for being data-hungry. The ability to explain its decision is essential for developing a responsible and robust decision system (Guidotti et al., 2019). On the other hand, logic programming methods, in the form of first-order logic (FOL), are capable of discovering and representing knowledge in explicit symbolic structure that can be understood and examined by human (Evans & Grefenstette, 2018). In this paper, we investigate the learning to explain problem in the scope of inductive logic programming (ILP) which seeks to learn first-order logic rules that explain the data. Traditional ILP methods (Gal arraga et al., 2015) relies on hard matching and discrete logic for rule search which is not tolerant for ambiguous and noisy data (Evans & Grefenstette, 2018). A number of works are proposed for developing differentiable ILP models that combine the strength of neural and logic-based computation (Y ang et al., 2017; Evans & Grefenstette, 2018; Campero et al., 2018; Rockt aschel & Riedel, 2017; Payani & Fekri, 2019).

This paper attempts to answer a central question in unsupervised learning: what does it mean to "make sense" of a sensory sequence? In our formalization, making sense involves constructing a symbolic causal theory that explains the sensory sequence and satisfies a set of unity conditions. This model was inspired by Kant's discussion of the synthetic unity of apperception in the Critique of Pure Reason. On our account, making sense of sensory input is a type of program synthesis, but it is unsupervised program synthesis. Our second contribution is a computer implementation, the Apperception Engine, that was designed to satisfy the above requirements. Our system is able to produce interpretable human-readable causal theories from very small amounts of data, because of the strong inductive bias provided by the Kantian unity constraints. A causal theory produced by our system is able to predict future sensor readings, as well as retrodict earlier readings, and "impute" (fill in the blanks of) missing sensory readings, in any combination. We tested the engine in a diverse variety of domains, including cellular automata, rhythms and simple nursery tunes, multi-modal binding problems, occlusion tasks, and sequence induction IQ tests. In each domain, we test our engine's ability to predict future sensor values, retrodict earlier sensor values, and impute missing sensory data. The Apperception Engine performs well in all these domains, significantly out-performing neural net baselines. We note in particular that in the sequence induction IQ tasks, our system achieved human-level performance. This is notable because our system is not a bespoke system designed specifically to solve IQ tasks, but a general purpose apperception system that was designed to make sense of any sensory sequence.

Silas: High Performance, Explainable and V erifiable Machine Learning Hadrien Bride, Zh e H ou Griffith University, Nathan, Brisbane, Australia Jie Dong Dependable Intelligence Pty Ltd, Brisbane, Australia Jin Song Dong National University of Singapore, Singapore Ali Mirjalili Griffith University, Nathan, Brisbane, AustraliaAbstract This paper introduces a new classification tool named Silas, which is built to provide a more transparent and dependable data analytics service. A focus of Silas is on providing a formal foundation of decision trees in order to support logical analysis and verification of learned prediction models. This paper describes the distinct features of Silas: The Model Audit module formally verifies the prediction model against user specifications, the Enforcement Learning module trains prediction models that are guaranteed correct, the Model Insight and Prediction Insight modules reason about the prediction model and explain the decision-making of predictions. We also discuss implementation details ranging from programming paradigm to memory management that help achieve high-performance computation.1. Introduction Machine learning has enjoyed great success in many research areas and industries, including entertainment [1], self-driving cars [2], banking [3], medical diagnosis [4], shopping [5], and among many others. However, the wide adoption of machine learn-Preprint submitted to Elsevier October 4, 2019 arXiv:1910.01382v1 The ramifications of the black-box approach are multifold. First, it may lead to unexpected results that are only observable after the deployment of the algorithm. For instance, Amazon's Alexa offered porn to a child [6], a self-driving car had a deadly accident [7], etc. Some of these accidents result in lawsuits or even lost lives, the cost of which is immeasurable. Second, it prevents the adoption in some applications and industries where an explanation is mandatory or certain specifications must be satisfied. For example, in some countries, it is required by law to give a reason why a loan application is rejected. In recent years, eXplainable AI (XAI) has been gaining attention, and there is a surge of interest in studying how prediction models work and how to provide formal guarantees for the models. A common theme in this space is to use statistical methods to analyse prediction models.

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.