Książki, monografie, podręczniki, rozdziały (WEEIiA)
Stały URI dla kolekcjihttp://hdl.handle.net/11652/171
Przeglądaj
2 wyniki
collection.search.results.head
Pozycja Grounded HyperSymbolic Representations Learned through Gradient-Based Optimization(Wydawnictwo Politechniki Łódzkiej, 2023) Łuczak, Piotr; Ślot, Krzysztof; Kucharski, JacekHyperdimensional computing is a novel paradigm, capable of processing complex data structures with simple operations. Its main limitations lie in the conversion of real world data onto hyperdimensional space, which due to lack of a universal translation scheme, oftentimes requires application-specific methods. This work presents a novel method for unsupervised hyperdimensional conversion of arbitrary image data. Additionally, this method is augmented by the ability of creating HyperSymbols, or class prototypes, provided that such class labels are available. The proposed method achieves promising performance on MNIST dataset, both in translating individual samples as well as producing HyperSymbols for downstream classification task.Pozycja Fuzzy logic approach proposal for human-robot interaction modelling(Wydawnictwo Politechniki Łódzkiej, 2016) Kosiński, Tomasz; Kucharski, JacekScientists need to look into the future and address the issues not yet anticipated in the society, especially those directly concerning its members safety and life. It is not a new conclusion to say that robots are becoming more and more sophisticated in their forms and actions. The humanity will soon face machines known to date from science-fiction literature only- resembling humans by appearance and behavior to an utmost extent. In the presented work, the Authors have proposed a fuzzy logic approach for Human-Robot Interaction (HRI) modelling, considering factors of two levels of interaction between a person and a machine: physical and psychological. The factors are, respectively: the distance between a person and a robot and the robot's performance, defined also using reliability and dependability terms. The proposal was based mainly on the qualitative knowledge obtained from the HRI experiments, with a support of available, limited quantitative data. This is to assure that when the sophisticated robot will knock at human's door, it will be able to interact with him in a way as close to seamless as possible. It is worth to note that the presented chapter proposes ( 1) a formalized modelling approach for HRI research work purposes and (2) the use of fuzzy logic to model intuitively·understood and interpreted relations between humans and robots.