A neuro fuzzy position controller for a servomotor, which is a nonlinear controller and gives much higher control performance for higly nonlinear systems than a linear controller, is proposed. that it is robust and ha...
详细信息
A neuro fuzzy position controller for a servomotor, which is a nonlinear controller and gives much higher control performance for higly nonlinear systems than a linear controller, is proposed. The simulation results s...
详细信息
With a proper combination of compliant and position- controlled joints, a link system can change its posture with keeping contact between link system and environment. This motion is so-called Self-Posture Changing Mot...
详细信息
The methods based on the traditional symbolic logic or the dynamic programming have been used to solve the longest common subsequences (LCS) between two given strings so far, which have many difficulties in the parall...
详细信息
There is a need for highly redundant manipulators to work in complex, cluttered environments. We explore kinematics and path planning for highly redundant, manipulators by means of a continuous manipulator model, whic...
详细信息
Two 2-layer networks are first trained independently by delta rule and then cascaded. The middle layer can be viewed as a hidden layer and is trained to attain preassigned saturated outputs in response to the training...
详细信息
Two 2-layer networks are first trained independently by delta rule and then cascaded. The middle layer can be viewed as a hidden layer and is trained to attain preassigned saturated outputs in response to the training set. Simulation results reveal that generalization ability of this cascaded network is far better than that of conventional back-propagation networks. Suggestions about the hidden coding in the cascaded network are presented. This network also learns considerably faster than BP networks. In large scale integrated neural network systems this network would enhance the overall performance.< >
A cross talk reduction method of an associative memory based on the outer product algorithm is presented. Because of crosstalk among superposed memories, memory capacity is limited and is much too low. To increase mem...
详细信息
A cross talk reduction method of an associative memory based on the outer product algorithm is presented. Because of crosstalk among superposed memories, memory capacity is limited and is much too low. To increase memory capacity, extensions to a higher-order correlation memory have been proposed. An associative memory architecture for realizing crosstalk reduction by using cross products as small as possible is presented. Higher-order cross product terms are obtained by using the Krawtchouk polynomial.< >
Design of a diagnostic technique used in an intelligent support system for artificial heart control is presented. Parameters which may cause abnormal variables of the recipient of artificial hearts are searched with t...
详细信息
Design of a diagnostic technique used in an intelligent support system for artificial heart control is presented. Parameters which may cause abnormal variables of the recipient of artificial hearts are searched with the use of a large dynamic model Human. The advantage of this technique is that candidates of abnormal parameters can be pointed out avoiding real-time parameter estimation whose results would be unreliable for the large scale model.
The authors investigate the generalization ability of the network generated by S.E. Fahlman and C. Lebiere's (FL) (1990) learning algorithm which has a distinctive feature to build any network topology. They train...
详细信息
The authors investigate the generalization ability of the network generated by S.E. Fahlman and C. Lebiere's (FL) (1990) learning algorithm which has a distinctive feature to build any network topology. They trained the same three-layer network by the FL algorithm and the backpropagation (BP) algorithm, and a comparison of recognition abilities shows that the FL network performs much better than the BP network. The FL network performs better because, in this network, hidden units use only saturated values and thus the hidden layer acts as a filter for noise. A two-layer network performs excellently if the training set is trainable by the two-layer network and if a pattern is recognized by detecting the maximum valued output. Since the FL algorithm begins with a minimal two-layer network which performs best under the condition stated, a designer can construct either a two-layer or a multilayer network according to which one best fits a particular application. Thus, it can be concluded that in all these respects the FL algorithm is preferable to the BP algorithm.< >
暂无评论