Search Results for author: Yoshihiro Maruyama

Found 6 papers, 0 papers with code

Computing with Categories in Machine Learning

no code implementations7 Mar 2023 Eli Sennesh, Tom Xu, Yoshihiro Maruyama

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.

Transfer Learning Variational Inference

A Probabilistic Generative Model of Free Categories

no code implementations9 May 2022 Eli Sennesh, Tom Xu, Yoshihiro Maruyama

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.

Variational Inference

The Artificial Scientist: Logicist, Emergentist, and Universalist Approaches to Artificial General Intelligence

no code implementations5 Oct 2021 Michael Timothy Bennett, Yoshihiro Maruyama

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 explore two theories that satisfy this requirement to some degree.

Philosophical Specification of Empathetic Ethical Artificial Intelligence

no code implementations22 Jul 2021 Michael Timothy Bennett, Yoshihiro Maruyama

An ethical AI must be capable of inferring unspoken rules, interpreting nuance and context, possess and be able to infer intent, and explain not just its actions but its intent.

Sentence

Intensional Artificial Intelligence: From Symbol Emergence to Explainable and Empathetic AI

no code implementations23 Apr 2021 Michael Timothy Bennett, Yoshihiro Maruyama

An agent possessed of it has a rationale for its decisions in terms of that purpose, expressed in a perceptual symbol system grounded in hardware.

Explainable artificial intelligence

Feature visualization of Raman spectrum analysis with deep convolutional neural network

no code implementations27 Jul 2020 Masashi Fukuhara, Kazuhiko Fujiwara, Yoshihiro Maruyama, Hiroyasu Itoh

Common component extraction is confirmed by an evaluation of numerically mixed amino acid spectra.

Cannot find the paper you are looking for? You can Submit a new open access paper.