- 1、本文档共11页,可阅读全部内容。
- 2、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。
- 3、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。
- 4、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)。
查看更多
Optimal Brain Surgeon Algorithm
ECE 539 Final Project
Mark Slosarek
9014829809Introduction:
For this project I am performing the optimal brain surgery algorithm. This algorithm is a pruning algorithm that reduces the connection between layers thus making it more efficient. A pruned network has several advantages. First, it needs smaller storage space. Second, it spends shorter time in calculation. Reducing a neural networks complexity improves the ability of the network to generalize future examples.
Work Performed:
The Optimal Brain Surgery Algorithm is based on the MLP Feed-forward Model similar to that described in Lecture 9 MLP (I): Feed-forward Model of professor Hu’s notes.
Figure 1: A Three Layer Feed-Forward Multi-layer Perceptron
In implementing the Optimal Brain Surgeon Algorithm, I implemented six steps as described in Neural Networks: A comprehensive Foundation by Simon Haykin.
Train the given multilayer perceptron to minimum mean-square error
Use the multilayer perceptron model with two hidden layers and one output neutron (three layer feed-forward multilayer perceptron) to compute the vectorwhere is the input-output mapping realized by the multilayer perceptron with an overall weight vector , and is the input vector.
Use the recursion to calculate the inverse Hessian
Find the that corresponds to the smallest saliency:where is the element of . If the saliency is much smaller than the mean square, , then delete synaptic weight , and proceed to step 4. Otherwise, go to 5.
Update all the synaptic weights in the network by applying the adjustment:Go to step 2.
Stop the computation when no more weights can be deleted from the network without a large increase in the mean-square error.
To truly implement this solution many different loops had to be implemented. These loops ended up being very cost effective on the computer and so I implemented a weight removal system that applied an algorithm that removed more weights. Although this was more ef
您可能关注的文档
- 自主探究在教学中的实际应用及理解.doc
- 组合式不锈钢水箱技术标准及安装规范.doc
- 资本资产定价模型的适用性及发展探讨.doc
- 自然科学基金合作协议书模板.doc
- 遵循《语文课程标准》,切实改进习作教学.DOC
- -5文物本体保护范围内的保存环境治理预(概)算.DOC
- 1余热锅炉设计时节点温差和接近点温差的选择.doc
- 1-12个月婴儿亲子游精典集.doc
- 20082009年度余姚阳明税务师事务所文明单位创建工.doc
- 2008级(3+2)应用电子技术专业人才培养方案.DOC
- 中国国家标准 GB/T 28182-2024额定电压52 kV及以下带串联间隙避雷器.pdf
- GB/T 28182-2024额定电压52 kV及以下带串联间隙避雷器.pdf
- 《GB/T 44045-2024石油、石化和天然气工业用转子泵》.pdf
- GB/T 15314-2024精密工程测量规范.pdf
- 中国国家标准 GB/T 15314-2024精密工程测量规范.pdf
- 《GB/T 15314-2024精密工程测量规范》.pdf
- GB/T 33475.2-2024信息技术 高效多媒体编码 第2部分:视频.pdf
- 中国国家标准 GB/T 33475.2-2024信息技术 高效多媒体编码 第2部分:视频.pdf
- 《GB/T 33475.2-2024信息技术 高效多媒体编码 第2部分:视频》.pdf
- GB/T 44045-2024石油、石化和天然气工业用转子泵.pdf
文档评论(0)