个人信息Personal Information
副教授
博士生导师
硕士生导师
性别:女
毕业院校:大连理工大学
学位:博士
所在单位:数学科学学院
学科:计算数学
办公地点:大连理工大学数学科学学院505
联系方式:0411-84708351-8205
电子邮箱:yangjiee@dlut.edu.cn
Binary Higher Order Neural Networks for Realizing Boolean Functions
点击次数:
论文类型:期刊论文
发表时间:2011-05-01
发表刊物:IEEE TRANSACTIONS ON NEURAL NETWORKS
收录刊物:SCIE、EI、PubMed
卷号:22
期号:5
页面范围:701-713
ISSN号:1045-9227
关键字:Binary pi-sigma neural network; binary product-unit neural network; Boolean function; principle conjunctive normal form; principle disjunctive normal form
摘要:In order to more efficiently realize Boolean functions by using neural networks, we propose a binary product-unit neural network (BPUNN) and a binary pi-sigma neural network (BPSNN). The network weights can be determined by one-step training. It is shown that the addition "sigma," the multiplication " pi," and two kinds of special weighting operations in BPUNN and BPSNN can implement the logical operators ".," ".," and " -" on Boolean algebra < Z(2), boolean OR, boolean AND, - 0, 1 > (Z(2) = {0, 1}), respectively. The proposed two neural networks enjoy the following advantages over the existing networks: 1) for a complete truth table of N variables with both truth and false assignments, the corresponding Boolean function can be realized by accordingly choosing a BPUNN or a BPSNN such that at most 2(N-1) hidden nodes are needed, while O(2(N)), precisely 2(N) or at most 2(N), hidden nodes are needed by existing networks; 2) a new network BPUPS based on a collaboration of BPUNN and BPSNN can be defined to deal with incomplete truth tables, while the existing networks can only deal with complete truth tables; and 3) the values of the weights are all simply -1 or 1, while the weights of all the existing networks are real numbers. Supporting numerical experiments are provided as well. Finally, we present the risk bounds of BPUNN, BPSNN, and BPUPS, and then analyze their probably approximately correct learnability.