Kyutacar : Kyushu Institute of Technology Academic Repository
Not a member yet
9746 research outputs found
Sort by
A Hippocampus-Inspired Memory Model with an Accumulation Function Through Place Representation Planes for Digital VLSI Implementation
Full text linkThe 12th RIEC International Symposium on Brain Functions and Brain Computer, February 27-28, 2024, Tohoku University, Sendai, Japanconference pape
An Intuitive and Traceable Human-based Evolutionary Computation System for Solving Problems in Human Organizations
Full text linkHuman-based evolutionary computation (EC), for which people act as executors of all evolutionary operators, can be used to solve problems in human organizations. We previously developed a human-based EC system that represents solutions as tags (words) and allows people to evaluate solutions by clicking corresponding tags. Although the system was easy and intuitive to use, it could not handle problems for which solutions are represented as long sentences. In addition, the system could not trace the evolution of solutions. Traceability is a must for the system to be widely and reliably used. In this study, we thus develop a human-based EC system that allows solutions to be represented as both sentences and tags. A function for tracing the evolution of solutions is embedded into the system. The function asks a solution creator to specify which existing solutions influenced the solution creation. We conduct an experiment in which 18 human subjects use the system and then fill out a survey. The results show that the system creates better solutions than those created by each human subject independently. Furthermore, the evolution tree generated from the information given by solution creators is used to confirm that the system allows the evolution of solutions to be traced.Worksop of Interactive Methods @ GECCO (iGECCO 2019) in The Genetic and Evolutionary Computation Conference (GECCO-2019),14th July, 2019, Prague, Czechconference pape
Robustness of Spiking Neural Networks Based on Time-to-First-Spike Encoding Against Adversarial Attacks
Full text linkSpiking neural networks (SNNs) more closely mimic the human brain than artificial neural networks (ANNs). For SNNs, time-to-first-spike (TTFS) encoding, which represents the output values of neurons based on the timing of a single spike, has been proposed as a promising model to reduce power consumption. Adversarial attacks that can lead ANNs to misrecognize images have been reported in many studies. However, the characteristics of TTFS-based SNNs trained using a backpropagation algorithm against adversarial attacks have not yet been clarified. In particular, the dependence of the robustness against adversarial attacks on spike timings has not been investigated. In this brief, we investigated the robustness of SNNs against adversarial attacks and compared it with that of an ANN. We found that SNNs trained with the appropriate temporal penalty settings are more robust against adversarial images than ANNs.journal articl
A Study on MAC Protocol of Uplink Multi-User for IEEE802.11ax
Full text link2016年電子情報通信学会総合大会, 2016年3月15日～18日, 九州大学, 福岡conference pape
FPGA-based Sensorless Control Strategy for Permanent Magnet Synchronous Motor using High-Frequency Injection with Loaded Start-up Capability
Full text link九州工業大学九州工業大学博士学位論文（要旨）学位記番号:生工博甲第514号 学位授与年月日:令和7年9月25日thesi
リザバー・コンピューティング・アーキテクチャを用いた低コスト人間行動認識
Full text link九州工業大学九州工業大学博士学位論文（要旨）学位記番号:生工博甲第517号 学位授与年月日:令和7年9月25日thesi