TY - JOUR
T1 - Common mistakes in neural network training
AU - Tien, D.
N1 - Publisher Copyright:
© 2003 IF AC.
PY - 2003
Y1 - 2003
N2 - Although artificial neural networks are not really considered to be similar to biological neural networks, the metaphor is strong enough when we describe the activities such as behaviour or reactions to various inputs. Artificial neural network systems are based on biological neurons. Researchers in the neural network are often failed to have a full understanding of the hypotheses and synthesize. This paper is based on and an extension of author's present and past work to highlight this problem. IF AC.
AB - Although artificial neural networks are not really considered to be similar to biological neural networks, the metaphor is strong enough when we describe the activities such as behaviour or reactions to various inputs. Artificial neural network systems are based on biological neurons. Researchers in the neural network are often failed to have a full understanding of the hypotheses and synthesize. This paper is based on and an extension of author's present and past work to highlight this problem. IF AC.
KW - Biological neuron
KW - Neural network
KW - Supervised and unsupervised training algorithms
UR - http://www.scopus.com/inward/record.url?scp=85064415297&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85064415297&partnerID=8YFLogxK
U2 - 10.1016/S1474-6670(17)33533-4
DO - 10.1016/S1474-6670(17)33533-4
M3 - Article
AN - SCOPUS:85064415297
SN - 1474-6670
VL - 36
SP - 383
EP - 385
JO - IFAC Proceedings Volumes (IFAC-PapersOnline)
JF - IFAC Proceedings Volumes (IFAC-PapersOnline)
IS - 15
T2 - 5th IFAC Symposium on Modelling and Control in Biomedical Systems 2003
Y2 - 21 August 2003 through 23 August 2003
ER -