TY - GEN
T1 - Learning of inverse kinematics using a neural network with efficient weights tuning ability
AU - Nagata, Fusaomi
AU - Inoue, Shota
AU - Fujii, Satoru
AU - Otsuka, Akimasa
AU - Watanabe, Keigo
PY - 2015/9/30
Y1 - 2015/9/30
N2 - Generally, in making a neural network learn nonlinear relations properly, desired training set are used. The training set consists of multiple pairs of an input vector and an output one. Each input vector is given to the input layer for forward calculation, and the corresponding output vector is compared with the vector yielded from the output layer. Also, weights are updated using a back propagation algorithm in backward calculation. The time required for the learning process of the neural network depends on the number of total weights in the neural network and the one of the input-output pairs in the training set. In the proposed learning process, after the learning is progressed e.g., 200 iterations, input-output pairs having had worse errors are extracted from the original training set and form a new temporary set. From the next iteration, the temporary set is applied instead of the original set. In this case, only pairs with worse errors are used for updating the weights until the mean value of errors reduces to a level. After the learning conducted using the temporary set, the original set is applied again instead of the temporary set. It is expected by alternately applying the above two types of sets for iterative learning that the convergence time can be efficiently reduced. The effectiveness is proved through simulation experiments using a kinematic model of a leg with four-DOFs.
AB - Generally, in making a neural network learn nonlinear relations properly, desired training set are used. The training set consists of multiple pairs of an input vector and an output one. Each input vector is given to the input layer for forward calculation, and the corresponding output vector is compared with the vector yielded from the output layer. Also, weights are updated using a back propagation algorithm in backward calculation. The time required for the learning process of the neural network depends on the number of total weights in the neural network and the one of the input-output pairs in the training set. In the proposed learning process, after the learning is progressed e.g., 200 iterations, input-output pairs having had worse errors are extracted from the original training set and form a new temporary set. From the next iteration, the temporary set is applied instead of the original set. In this case, only pairs with worse errors are used for updating the weights until the mean value of errors reduces to a level. After the learning conducted using the temporary set, the original set is applied again instead of the temporary set. It is expected by alternately applying the above two types of sets for iterative learning that the convergence time can be efficiently reduced. The effectiveness is proved through simulation experiments using a kinematic model of a leg with four-DOFs.
KW - Efficient weights tuning
KW - Inverse kinematics
KW - Leg with multi-DOFs
KW - Neural network
KW - Temporary training set
UR - http://www.scopus.com/inward/record.url?scp=84960153753&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84960153753&partnerID=8YFLogxK
U2 - 10.1109/SICE.2015.7285331
DO - 10.1109/SICE.2015.7285331
M3 - Conference contribution
AN - SCOPUS:84960153753
T3 - 2015 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015
SP - 1042
EP - 1046
BT - 2015 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 54th Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2015
Y2 - 28 July 2015 through 30 July 2015
ER -