- 1、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。。
- 2、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
- 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
- 5、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们。
- 6、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 7、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
[管理学]On-line learning through simple perceptron with a margin
ON-LINE LEARNING THROUGH SIMPLE
3 PERCEPTRON LEARNING WITH A MARGIN
0
0
2
n
u Kazuyuki Hara†
J
5
] †Department of Electronics and Information Engineering,
n
n
s- Tokyo Metropolitan College of Technology
i
d
.
t †1-10-40 Higashi-oi, Shinagawa-ku, Tokyo 140-0011, Japan.
a
m
- Tel: 03-3471-6331, Fax: 03-3471-6338, E-mail: hara@tokyo-tmct.ac.jp
d
n
o
c Masato Okada‡
[
1
v
0 ‡Laboratory for Mathematical Neuroscience,
5
1 Brain Science Institute, RIKEN
6
0
3
0 ‡ 2-1 Hirosawa, Wako-shi, Saitama, 351-0198,Japan.
/
t
a Tel: 048-467-6845, Fax: 048-467-7349, E-mail: okada@brain.riken.go.jp
m
-
d
n
o Acknowledgement Part of this study has been supported by Grant-in-Aid
c
:
v
i for Scientific Research on Priority Area No. and Grant-in-Aid for
X
r Scientific Research (C) No. and No.
a
running head
On-Line Learning with a margin
On-Line Learning with a margin 1
Abstract
We analyze a learning method that uses a margin κ a la Gardner for sim-
ple perceptron learning. This method corresponds to the perceptron learning
when κ = 0, and to the Hebbian learning when κ → ∞. Nevertheless, we
found that the generalization ability of the method was superior to that of
the perceptron and the Hebbian methods at an early stage of learning. We an-
alyzed the asymptotic property of the learning
文档评论(0)