| Tweet | |
| E. Aliwarga, J. Yu, M. Hatanaka, and T. Onoye, "Hardware Architecture of Generic Soft Cascaded Linear Svm Classifier," 75, 電子情報通信学会ディペンダブルコンピューティング研究会, June 2015. | |
| ID | 824 |
| 分類 | 研究会等発表論文 |
| タグ | |
| 表題 (title) |
Hardware Architecture of Generic Soft Cascaded Linear Svm Classifier |
| 表題 (英文) |
Hardware Architecture of Generic Soft Cascaded Linear Svm Classifier |
| 著者名 (author) |
E. Aliwarga,J. Yu,M. Hatanaka,T. Onoye |
| 英文著者名 (author) |
|
| キー (key) |
Eric Aliwarga,Jaehoon Yu , Masahide Hatanaka, Takao Onoye |
| 号数 (number) |
75 |
| 技術報告書の種別 (type) |
|
| 発行元組織 (organization) |
電子情報通信学会ディペンダブルコンピューティング研究会 |
| 出版社住所 (address) |
|
| 刊行月 (month) |
6 |
| 出版年 (year) |
2015 |
| URL |
|
| 付加情報 (note) |
|
| 注釈 (annote) |
|
| 内容梗概 (abstract) |
Support Vector Machine is renowned as a powerful machine learning algorithm for many classi cation problems. However, among all the works proposed for SVM hardware implementation, a lot of them are designed solely for speci c purpose. This paper presents an SVM hardware architecture capable of classifying input data with arbitrary vector dimensionality and arbitrary precision, resulting in a generic support vector machine capable of classifying various targets. The proposed architecture also employs a speed-up method called soft cascade algorithm to enhance its performance. The results show that for CoHOG pedestrian detection, the proposed hardware architecture may classify up to 77 VGA images per second even under the condition that the architecture is not designed speci cally for the mentioned purpose. |
| 論文電子ファイル | 利用できません． |
| BiBTeXエントリ |
@techreport{id824,
title = {Hardware Architecture of Generic Soft Cascaded Linear SVM Classifier},
author = {E. Aliwarga and J. Yu and M. Hatanaka and T. Onoye},
number = {75},
institution = {電子情報通信学会ディペンダブルコンピューティング研究会},
month = {6},
year = {2015},
}
|