An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the ...An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the input layer depends on the dimensionality of input patterns. The number of neurons in the output layer equals the number of the desired classes. The number of neurons in the Kohonen layer may be a few to several thousands, which depends on the complexity of classification problems and the classification precision. Each training sample is expressed by a pair of vectors ： an input vector and a class codebook vector. When a training sample is input into the model, Kohonen＇s competitive learning rule is applied to selecting the winning neuron from the Kohouen layer and the weight coefficients connecting all the neurons in the input layer with both the winning neuron and its neighbors in the Kohonen layer are modified to be closer to the input vector, and those connecting all the neurons around the winning neuron within a certain diameter in the Kohonen layer with all the neurons in the output layer are adjusted to be closer to the class codebook vector. If the number of training sam- ples is sufficiently large and the learning epochs iterate enough times, the model will be able to serve as a supervised classifier. The model has been tentatively applied to the supervised classification of multispectral remotely sensed data. The author compared the performances of the extended SOM and BPN in remotely sensed data classification. The investigation manifests that the extended SOM is feasible for supervised classification.展开更多
This paper is about the automation of the marionette performance. A method to solve the problem on the mobility of the automated marionette performance is proposed. Since it is difficult to control the marionette by h...This paper is about the automation of the marionette performance. A method to solve the problem on the mobility of the automated marionette performance is proposed. Since it is difficult to control the marionette by hands, as an alternative, the automated marionette is studied. However, the automtic marionette performance is limited in the silence and mobility. Therefore, an independent shifter to move freely on the stage is required. The magnetic device which connects the movable robot and the marionette controlling robot is conceived. The magnetic device is improved and applied by considering the features of the marionette robot, which is the irregular movement of the marionette controller and of the parallel limited area. The burden of being trapped on the magnet is minimized by dividing the robot to the upper and lower parts of the marionette performance stage. The direction of the magnet is considered to make the mobile robot to move freely. Thus, the efficiency and safety of the device is confirmed by balancing the strength with the permanent magnet.展开更多
1.引言 在母语习得研究领域里,一个颇具争议的问题是:儿童语言中的泛化错误(overgeneralization errors)是如何消失的?请看下列句子: (1) a. He gave a book to John.(他把一本书给了约翰。) b. He gave John a book.(他给约翰一本书。)...1.引言 在母语习得研究领域里,一个颇具争议的问题是:儿童语言中的泛化错误(overgeneralization errors)是如何消失的?请看下列句子: (1) a. He gave a book to John.(他把一本书给了约翰。) b. He gave John a book.(他给约翰一本书。) (2) a. He donated a painting to the museum.(他把一幅画赠给博物馆。) b. He donated the museum a painting.(他赠给博物馆一幅画。)展开更多
基金Supported by National Natural Science Foundation of China (No. 40872193)
文摘An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the input layer depends on the dimensionality of input patterns. The number of neurons in the output layer equals the number of the desired classes. The number of neurons in the Kohonen layer may be a few to several thousands, which depends on the complexity of classification problems and the classification precision. Each training sample is expressed by a pair of vectors ： an input vector and a class codebook vector. When a training sample is input into the model, Kohonen＇s competitive learning rule is applied to selecting the winning neuron from the Kohouen layer and the weight coefficients connecting all the neurons in the input layer with both the winning neuron and its neighbors in the Kohonen layer are modified to be closer to the input vector, and those connecting all the neurons around the winning neuron within a certain diameter in the Kohonen layer with all the neurons in the output layer are adjusted to be closer to the class codebook vector. If the number of training sam- ples is sufficiently large and the learning epochs iterate enough times, the model will be able to serve as a supervised classifier. The model has been tentatively applied to the supervised classification of multispectral remotely sensed data. The author compared the performances of the extended SOM and BPN in remotely sensed data classification. The investigation manifests that the extended SOM is feasible for supervised classification.
基金supported bythe Ministry of Knowledge Economy,Korea,theITRC(Information Technology Research Center)support program(NIPA-2010-(C1090-1021-0010))the Brain Korea 21 Project in 2010
文摘This paper is about the automation of the marionette performance. A method to solve the problem on the mobility of the automated marionette performance is proposed. Since it is difficult to control the marionette by hands, as an alternative, the automated marionette is studied. However, the automtic marionette performance is limited in the silence and mobility. Therefore, an independent shifter to move freely on the stage is required. The magnetic device which connects the movable robot and the marionette controlling robot is conceived. The magnetic device is improved and applied by considering the features of the marionette robot, which is the irregular movement of the marionette controller and of the parallel limited area. The burden of being trapped on the magnet is minimized by dividing the robot to the upper and lower parts of the marionette performance stage. The direction of the magnet is considered to make the mobile robot to move freely. Thus, the efficiency and safety of the device is confirmed by balancing the strength with the permanent magnet.
文摘1.引言 在母语习得研究领域里,一个颇具争议的问题是:儿童语言中的泛化错误(overgeneralization errors)是如何消失的?请看下列句子: (1) a. He gave a book to John.(他把一本书给了约翰。) b. He gave John a book.(他给约翰一本书。) (2) a. He donated a painting to the museum.(他把一幅画赠给博物馆。) b. He donated the museum a painting.(他赠给博物馆一幅画。)
