Search Results for author: Tomoaki Niiyama

Found 5 papers, 0 papers with code

Optical hyperdimensional soft sensing: Speckle-based touch interface and tactile sensor

no code implementations6 Jan 2024 Kei Kitagawa, Kohei Tsuji, Koyo Sagehashi, Tomoaki Niiyama, Satoshi Sunada

Hyperdimensional computing (HDC) is an emerging computing paradigm that exploits the distributed representation of input data in a hyperdimensional space, the dimensions of which are typically between 1, 000--10, 000.

Ultrafast single-channel machine vision based on neuro-inspired photonic computing

no code implementations15 Feb 2023 Tomoya Yamaguchi, Kohei Arai, Tomoaki Niiyama, Atsushi Uchida, Satoshi Sunada

This approach allows for compressive acquisitions of visual information with a single channel at gigahertz rates, outperforming conventional approaches, and enables its direct photonic processing using a photonic reservoir computer in a time domain.

Anomaly Detection

Optical skin: Sensor-integration-free multimodal flexible sensing

no code implementations3 Feb 2022 Sho Shimadera, Kei Kitagawa, Koyo Sagehashi, Tomoaki Niiyama, Satoshi Sunada

The proposed approach is based on an optical interference technique, which can encode the information of various stimuli as a spatial pattern.

Physical deep learning based on optimal control of dynamical systems

no code implementations16 Dec 2020 Genki Furuhata, Tomoaki Niiyama, Satoshi Sunada

In this study, we perform pattern recognition based on the optimal control of continuous-time dynamical systems, which is suitable for physical hardware implementation.

Lotka-Volterra competition mechanism embedded in a decision-making method

no code implementations29 Jul 2019 Tomoaki Niiyama, Genki Furuhata, Atsushi Uchida, Makoto Naruse, Satoshi Sunada

Decision making is a fundamental capability of living organisms, and has recently been gaining increasing importance in many engineering applications.

Decision Making Reinforcement Learning

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