Differentiable Logic Gate Networks (DLNs) offer a compelling framework for symbolic interpretability and reducing inference cost.Building on prior works using Menger and Zadeh T-norms, we investigate the Łukasiewicz T-norm as an alternative relaxation for classical logic gates.While it provides strong gradients in some regions, its flat areas result in vanishing gradients that hinder training.To address this issue, we use an initialization strategy that is analogous to residual connection in Neural Networks to encourage error signal propagation during training.Our empirical results show that Łukasiewicz based DLNs, though slightly less accurate, benefit from faster inference and lower memory requirements compared to Neural Networks, giving the opportunity of practical application in, e.g., resource constrained devices.Due to the structural clarity, DLNs facilitate direct inspection and tracing of information flow, which makes them suitable for application in explainable artificial intelligence (XAI).

Social choice function or voting procedure is one of the crucial concepts in the domain of political sciences.It maps individuals' preferences over a set of candidates to some subset (possibly one-element) of the candidates who can be thought as the winners of an election procedure.The paper is aimed at applications of formal concept analysis methods to study of social choice functions.We will construct concept lattices over selected set of social choice functions characterized by possessing some properties deemed as important from the point of view of political sciences.We will discuss issues connected with reducibility of both objects and attributes, irreducibility of object concepts as well as attribute concepts and attribute implications.We will discuss also the shape of the constructed concept lattice of social choice functions which in some part is exceptionally regular from the perspective of the lattice theory.

This special issue of Fundamenta Informaticae is dedicated to papers selected from the 26 th International Workshop on CONCURRENCY, SPECIFICATION, AND PROGRAMMING (CS&P 2017), which took place in Warsaw, Poland, in

The paper is aimed at comparing Rough Set Theory (RST) and Formal Concept Analysis (FCA) with respect to algebraic structures of concepts appearing in both theories, namely algebras of definable sets and concept lattices. The paper presents also basic ideas and concepts of RST and FCA together with some set theoretical concepts connected with set spaces which can serve as a convenient platform for a comparison of RST and FCA. In the last section there are shown necessary and sufficient conditions for the fact, that families of definable sets and concept extents determined by the same formal contexts are equal . This in finite cases is equivalent to an isomorphism of respective structures and generally reflects a very specific situation when both theories give the same conceptual hierarchies.

This paper is an attempt to introduce a notion of dialogue among different agents, e.g. a user or situation descriptor and an information provider or machine, to better understand a user’s need of information. When a user describes a concept through some keywords first the system needs to choose th e relevant attributes for initiating the search. Regarding this, a series of dialogues may help the system to better understand the user’s language of expresssion. After fixing the relevant attributes, the system needs to look at its repertoire of positive and negative cases of different concepts characterized with respect to this set of attributes. Then through a step-by-step process of matching and comparing similarity of user’s described situation with those positive and negative cases of a concept, incorporating several layers of dialogue, the system may provide information closer to the user’s need. The target of this paper is to develop a theoretical model, incorporating the above features, for characterizing one’s concern of concept based on dialogue and similarity based reasoning.

We discuss the rough set approach to approximation of vague concepts. There are already published several papers on rough sets and vague concepts staring from the seminal papers by Zdzisław Pawlak. However, only a few of them are discussing the relationships of rough sets with the sorites paradox. This paper contains a continuation of discussion on this issue.

This paper is an early report from research undertaken to meet the needs of the General Directorate for National Roads and Motorways of Poland. They have defined the task of estimating the annual average Daily Traffic on a class of highways in the country, based on a very small number of daily traffic measurements undertaken throughout the year (typically one or two such measurements). We report the data available to us, and the data preprocessing step, including the generation of additional attributes and generation of synthetic data. We use a deep neural network model of the annual count number, and we report encouraging early result. In the conclusion, we discuss the next steps of this research.

The paper presents a prototype radio network aiding the visually impaired in using the public transport. The main purpose of the network is to provide accurate and reliable location information as well as to enable access to location related context information. The data from radio nodes are used to facilitate the navigation in urban and indoor areas. Keeping up the connection with dedicated system servers gives access to additional services, e.g. enables the use of passenger information system and provides access to a database storing information on points of interest (POI) of different categories. The paper describes an overview of the system architecture. Then, the details of the positioning methods implemented in the solution are presented. Finally, the user-system interaction scenarios are discussed.

We present a method for improving the detection of outlying Fire Service's reports based on domain knowledge and dialogue with Fire & Rescue domain experts. The outlying report is considered as an element which is significantly different from the remaining data. We follow the position of Professor Andrzej Skowron that effective algorithms in data mining and knowledge discovery in big data should incorporate an interaction with domain experts or/and be domain oriented. Outliers are defined and searched on the basis of domain knowledge and dialogue with experts. We face the problem of reducing high data dimensionality without loosing specificity and real complexity of reported incidents. We solve this problem by introducing a knowledge based generalization level intermediating between analyzed data and experts domain knowledge. In our approach we use the Formal Concept Analysis methods for both generation of the appropriate categories from data and as tools supporting communication with domain experts. We conducted two experiments in finding two types of outliers in which outlier detection was supported by domain experts.