TY - GEN
T1 - Using dynamic expansion & contraction approach to generate a feedforward network
AU - Young, D.
AU - Cheng, L. M.
PY - 1994
Y1 - 1994
N2 - This paper proposes an algorithm to autonomously generate a feedforward network based on the input data. Dynamic expansion & contraction approach (DECA) is used to determine the optimal number of hidden node. The algorithm is applicable to the neural network used for function approximation and pattern classification. The short interval of train/test interleaving will minimize the learning time and avoid over-training the network. That is, a neural network for an application can be generated automatically in optimal time. Together with time-division-multiplexing architecture [1], A hardware reconfigurable ANN architecture with learning capabilities can be realised.
AB - This paper proposes an algorithm to autonomously generate a feedforward network based on the input data. Dynamic expansion & contraction approach (DECA) is used to determine the optimal number of hidden node. The algorithm is applicable to the neural network used for function approximation and pattern classification. The short interval of train/test interleaving will minimize the learning time and avoid over-training the network. That is, a neural network for an application can be generated automatically in optimal time. Together with time-division-multiplexing architecture [1], A hardware reconfigurable ANN architecture with learning capabilities can be realised.
UR - http://www.scopus.com/inward/record.url?scp=0028743136&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0028743136&origin=recordpage
M3 - RGC 32 - Refereed conference paper (with host publication)
VL - 3
SP - 1546
EP - 1549
BT - IEEE International Conference on Neural Networks - Conference Proceedings
PB - IEEE
T2 - Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
Y2 - 27 June 1994 through 29 June 1994
ER -