Zobrazeno 1 - 10
of 272
pro vyhledávání: '"Maruyama Yoshihiro"'
Category theory has been successfully applied in various domains of science, shedding light on universal principles unifying diverse phenomena and thereby enabling knowledge transfer between them. Applications to machine learning have been pursued re
Externí odkaz:
http://arxiv.org/abs/2303.04156
Autor:
NISHIMURA, Hirokazu
Publikováno v:
zbMATH Open.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=jairo_______::bd23f8e4cda47bd7e764ec14fac71582
https://tsukuba.repo.nii.ac.jp/records/2002402
https://tsukuba.repo.nii.ac.jp/records/2002402
Autor:
Bloomfield, Colin, Maruyama, Yoshihiro
We extend Lawvere-Pitts prop-categories (aka. hyperdoctrines) to develop a general framework for providing "algebraic" semantics for nonclassical first-order logics. This framework includes a natural notion of substitution, which allows first-order l
Externí odkaz:
http://arxiv.org/abs/2205.05657
Applied category theory has recently developed libraries for computing with morphisms in interesting categories, while machine learning has developed ways of learning programs in interesting languages. Taking the analogy between categories and langua
Externí odkaz:
http://arxiv.org/abs/2205.04545
Publikováno v:
Proceedings of the 14th International Conference on Artificial General Intelligence. 2021. Lecture Notes in Computer Science, vol 13154. Springer. pp. 45-54
We attempt to define what is necessary to construct an Artificial Scientist, explore and evaluate several approaches to artificial general intelligence (AGI) which may facilitate this, conclude that a unified or hybrid approach is necessary and explo
Externí odkaz:
http://arxiv.org/abs/2110.01831
Publikováno v:
IEEE Transactions on Cognitive and Developmental Systems, vol. 14, no. 2, pp. 292-300, June 2022
In order to construct an ethical artificial intelligence (AI) two complex problems must be overcome. Firstly, humans do not consistently agree on what is or is not ethical. Second, contemporary AI and machine learning methods tend to be blunt instrum
Externí odkaz:
http://arxiv.org/abs/2107.10715
We argue that an explainable artificial intelligence must possess a rationale for its decisions, be able to infer the purpose of observed behaviour, and be able to explain its decisions in the context of what its audience understands and intends. To
Externí odkaz:
http://arxiv.org/abs/2104.11573
Autor:
Bloomfield, Colin, Maruyama, Yoshihiro
Publikováno v:
In Journal of Pure and Applied Algebra February 2024 228(2)
Publikováno v:
Analytica Chimica Acta, Volume 1087, 9 December 2019, Pages 11-19
We demonstrate a recognition and feature visualization method that uses a deep convolutional neural network for Raman spectrum analysis. The visualization is achieved by calculating important regions in the spectra from weights in pooling and fully-c
Externí odkaz:
http://arxiv.org/abs/2007.13354