曾晓勤
机器学习、人工神经网络、机器视觉、模式识别、图文法和信息可视化等方面。
个性化签名
- 姓名:曾晓勤
- 目前身份:
- 担任导师情况:
- 学位:
-
学术头衔:
博士生导师
- 职称:-
-
学科领域:
计算机科学技术
- 研究兴趣:机器学习、人工神经网络、机器视觉、模式识别、图文法和信息可视化等方面。
曾晓勤,获南京大学学士学位、东南大学硕士学位、和香港理工大学博士学位,现任河海大学计算机与信息学院教授、博士生导师。
曾晓勤教授长期以来一直从事计算机科学及工程领域的教学与科研工作,讲授过多门计算机学科的专业基础课和专业课,成功主持和参加过国家自然科学基金项目、江苏省自然科学基金项目、以及美国和香港相应的基金项目。在国际和国内权威学术期刊上发表有多篇学术论文(如Neural Computation、IEEE Transactions on Neural Networks、中国科学-F辑等)。近些年来的研究兴趣主要包括:机器学习、人工神经网络、机器视觉、模式识别、图文法和信息可视化等方面。
曾晓勤教授是IEEE SMC 学会机器学习技术委员会委员、江苏省计算机学会人工智能专业委员会常务委员、国际学术期刊IEEE Transactions on Systems, Man, and Cybernetics-Part B 副编辑(Associate Editor)、和多个国际学术刊物的评审员(如EEE Transactions on Neural Networks、Information Science、Neurocomputing等),并是多个国际学术会议的程序委员会成员。
曾晓勤教授访问过美国德州大学、香港理工大学、和香港城市大学等学校,与相关研究邻域的国际学者有着密切的协作关系。
-
主页访问
4524
-
关注数
0
-
成果阅读
378
-
成果数
9
【期刊论文】A sensitivity-based approach for pruning architecture of Madalines
曾晓勤, Xiaoqin Zeng, Jing Shao, Yingfeng Wang, Shuiming Zhong
Neural Comput & Applic (2009) 18: 957-965,-0001,():
-1年11月30日
Architecture design is a very important issue in neural network research. One popular way to find proper size of a network is to prune an oversize trained network to a smaller one while keeping established performance. This paper presents a sensitivity-based approach to prune hidden Adalines from a Madaline with causing as little as possible performance loss and thus easy compensating for the loss. The approach is novel in setting up a relevance measure, by means of an Adalines'sensitivity measure, to locate the least relevant Adaline in a Madaline. The sensitivity measure is the probability of an Adaline's output inversions due to input variation with respect to overall input patterns, and the relevance measure is defined as the multiplication of the Adaline's sensitivity value by the summation of the absolute value of the Adaline's outgoing weights. Based on the relevance measure, a pruning algorithm can be simply programmed, which iteratively prunes an Adaline with the least relevance value from hidden layer of a given Madaline and then conducts some compensations until no more Adalines can be removed under a given performance requirement. The effectiveness of the pruning approach is verified by some experimental results.
Adaline, Madaline, Architecture pruning, Sensitivity measure, Relevance measure
-
45浏览
-
0点赞
-
0收藏
-
0分享
-
102下载
-
0评论
-
引用
曾晓勤, 曾晓勤+, 韩秀清, 邹阳
软件学报,2008,19(8):1893~1901,-0001,():
-1年11月30日
围绕解决图文法中的主要问题——嵌入问题,提出了一种基于边的上下文相关图文法形式化框架,并对由此定义的文法的一些性质及相应的归约算法进行了讨论。对所提出的图文法与已有的文法进行了比较。同时,展望了今后值得进一步研究的一些问题和方向。
可视化语言, 形式化, 图文法, 嵌入问题, 产生式
-
72浏览
-
0点赞
-
0收藏
-
0分享
-
89下载
-
0评论
-
引用
-
34浏览
-
0点赞
-
0收藏
-
0分享
-
121下载
-
0评论
-
引用
曾晓勤, Xiaoqin
IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 17, NO. 2, MARCH 2006,-0001,():
-1年11月30日
In
Adaline,
-
40浏览
-
0点赞
-
0收藏
-
0分享
-
143下载
-
0评论
-
引用
曾晓勤, Xiaoqin
X. Zeng, D. S. Yeung. Neurocomputing 69 (2006) 825-837,-0001,():
-1年11月30日
In
Neural
-
38浏览
-
0点赞
-
0收藏
-
0分享
-
221下载
-
0评论
-
引用
曾晓勤, Xiaoqin
IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 12, NO. 6, NOVEMBER 2001,-0001,():
-1年11月30日
An
Multilayer
-
35浏览
-
0点赞
-
0收藏
-
0分享
-
223下载
-
0评论
-
引用
曾晓勤, Xiaoqin
LETTER Communicated by Terrence Sejnowski Neural Computation 15, 183-212 (2003),-0001,():
-1年11月30日
The sensitivity of a neural network’s output to its input perturbation is an important issue with both theoretical and practical values. In this article, we propose an approach to quantify the sensitivity of the most popular and general feedforward network: multilayer perceptron (MLP). The sensitivity measure is de.ned as the mathematical expectation of output deviation due to expected input deviation with respect to overall input patterns in a continuous interval. Based on the structural characteristics of the MLP, a bottom-up approach is adopted. A single neuron is considered .rst, and algorithms with approximately derived analytical expressions that are functions of expected input deviation are given for the computation of its sensitivity. Then another algorithm is given to compute the sensitivity of the entireMLP network. Computer simulations are used to verify the derived theoretical formulas. The agreement between theoretical and experimental results is quite good. The sensitivity measure can be used to evaluate the MLP’s performance.
-
40浏览
-
0点赞
-
0收藏
-
0分享
-
102下载
-
0评论
-
引用
曾晓勤, Yingfeng Wang
LETTER Communicated by Andries P. Engelbrecht Neural Computation 18, 2854-2877 (2006),-0001,():
-1年11月30日
The sensitivity of a neural network’s output to its input and weight perturbations is an important measure for evaluating the network’s performance. In this letter, we propose an approach to quantify the sensitivity of Madalines. The sensitivity is defined as the probability of output deviation due to input and weight perturbations with respect to overall input patterns. Based on the structural characteristics of Madalines, a bottomup strategy is followed, along which the sensitivity of single neurons, that is, Adalines, is considered first and then the sensitivity of the entire Madaline network. By means of probability theory, an analytical formula is derived for the calculation of Adalines’ sensitivity, and an algorithm is designed for the computation of Madalines’ sensitivity. Computer simulations are run to verify the effectiveness of the formula and algorithm. The simulation results are in good agreement with the theoretical results.
-
43浏览
-
0点赞
-
0收藏
-
0分享
-
68下载
-
0评论
-
引用
曾晓勤, Xiaoqin
,-0001,():
-1年11月30日
This paper presents an approach to determine the relevance of individual input attributes for trained Multilayer Perceptrons (MLPs). To reflect the impact of an input attribute on the output of an MLP, the relevance is aimed at representing the output sensitivity of the MLP to the attribute variation. The sensitivity is defined as the mathematical expectation of output deviations of an MLP due to its input deviation with respect to overall input patterns. The basic idea for the introduction of such a relevance measure is that a well-trained MLP can capture salient features of the problem it deals with and thus become more sensitive to those input attributes that make more contributions to the MLP’s behavior. The relevance can be employed as a relative criterion for assessing individual input attributes. The results from the experiments on two typical problems demonstrate the effectiveness of the relevance in identifying irrelevant input attribute.
Neural
-
31浏览
-
0点赞
-
0收藏
-
0分享
-
106下载
-
0评论
-
引用