Since its emergence in the 1960s, Artificial Intelligence (AI) has grown to conquer many technology products and their fields of application. Machine learning, as a major part of the current AI solutions, can learn from the data and through experience to reach high performance on various tasks. This growing success of AI algorithms has led to a need for interpretability to understand opaque models such as deep neural networks. Various requirements have been raised from different domains, together with numerous tools to debug, justify outcomes, and establish the safety, fairness and reliability of the models. This variety of tasks has led to inconsistencies in the terminology with, for instance, terms such as interpretable, explainable and transparent being often used interchangeably in methodology papers. These words, however, convey different meanings and are “weighted" differently across domains, for example in the technical and social sciences. In this paper, we propose an overarching terminology of interpretability of AI systems that can be referred to by the technical developers as much as by the social sciences community to pursue clarity and efficiency in the definition of regulations for ethical and reliable AI development. We show how our taxonomy and definition of interpretable AI differ from the ones in previous research and how they apply with high versatility to several domains and use cases, proposing a—highly needed—standard for the communication among interdisciplinary areas of AI.

No abstract

No abstract

The aim of the paper is to present a new approach based on the Cellular Automata technique for a specific class of scheduling problems with parallel machines (in which some important parameter values cannot be determined a priori). The problem domain is represented by an asynchronous non-homogeneous cellular automaton. In addition, the division of the method into three levels is introduced. Inseparable use of simulation, optimization and result levels, is proposed. To illustrate our proposition, the optimization problem of drilling tunnels in a given area is considered. A number of simulation experiments were performed involving different instances of the problem and the results are presented and discussed in the paper.

No abstract

Abstract. The ALMM Solver is a software tool which aim is generating solutions for discrete optimization problems, in particular for NP-hard problems. The idea of the solver is based on Algebraic Logical MetaModel of Multistage Decision Process (ALMM of MDP). The aim of the paper is to present the architecture of the ALMM Solver and to describe requirements regarding the solver, in particular non-functional ones. SimOpt, the core module of the solver, is described in detail. The practices, design patterns and principles, that was used to ensure the best quality of the solver software, are mentioned in the paper.

No abstract