NEUROSCIENCE-INSPIRED RECURRENT NETWORK FOR OBJECT RECOGNITION

檔案

本條目沒有附加檔案。

日期

2017-01-01

期刊名稱

2017 INTERNATIONAL SYMPOSIUM ON INTELLIGENT SIGNAL PROCESSING AND COMMUNICATION SYSTEMS (ISPACS 2017)

卷期與頁次

頁 729–734

語言

英文

摘要

Deep neural networks inspired by the connections among biological neurons have been highly effective in the advancement of computer vision. Recent research into recurrent neural networks has taken account of forward as well as recurrent connections in a neural network architecture. In this study, we proposed a model that mirrors the architecture of the human ventral pathway with separate layers representing brain regions connected using long-range recurrent links. MAR 10/100 datasets were used to assess the performance of object recognition using the proposed model and the results were compared with those obtained using state-of-the-art methods. We demonstrated that the classification accuracy increased as the number of recurrences increased. Our results suggest that the proposed neuroscience-inspired model can facilitate object recognition in computer vision and may help to elucidate neurological mechanisms in the human brain.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

引用此條目

Chang, J.-R., Kuo, P.-C., & Chen, Y.-S. (2017). NEUROSCIENCE-INSPIRED RECURRENT NETWORK FOR OBJECT RECOGNITION. 2017 INTERNATIONAL SYMPOSIUM ON INTELLIGENT SIGNAL PROCESSING AND COMMUNICATION SYSTEMS (ISPACS 2017), 729–734. https://ir.lib.nycu.edu.tw/handle/11536/147204

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/147204