TY - GEN
T1 - Learning by choice of internal representations- Feed forward nets with binary weights
AU - Saad, D.
AU - Marom, E.
N1 - Publisher Copyright:
© Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991. All rights reserved.
PY - 1991
Y1 - 1991
N2 - Learning by choice of internal representations (CHIR) is a training algorithm for feed-forward(FF) neural networks, introduced by Grossman et alt [2], based upon determining the internal representations of the system as well as its internal weights. In a former paper[3] we have shown a method for deriving the CHIR algorithm, whereby the internal representations (IR) as well as the weights are allowed to be modified, via energy minimization consideration. This method is now applied for training a FF net with binary weights, supplying a convenient tool for training such a net. Computer simulations show a fast training process for this algorithm in comparison with the Back-Propagation[4] and the CHIR[1][2] algorithms, both used in conjunction with a feed-forward net with continuous weights. These simulations include the restricted cases of parity, symmetry and parity-symmetry problems.
AB - Learning by choice of internal representations (CHIR) is a training algorithm for feed-forward(FF) neural networks, introduced by Grossman et alt [2], based upon determining the internal representations of the system as well as its internal weights. In a former paper[3] we have shown a method for deriving the CHIR algorithm, whereby the internal representations (IR) as well as the weights are allowed to be modified, via energy minimization consideration. This method is now applied for training a FF net with binary weights, supplying a convenient tool for training such a net. Computer simulations show a fast training process for this algorithm in comparison with the Back-Propagation[4] and the CHIR[1][2] algorithms, both used in conjunction with a feed-forward net with continuous weights. These simulations include the restricted cases of parity, symmetry and parity-symmetry problems.
UR - http://www.scopus.com/inward/record.url?scp=85067607346&partnerID=8YFLogxK
U2 - 10.1109/EEIS.1991.217664
DO - 10.1109/EEIS.1991.217664
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85067607346
T3 - Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991
SP - 199
EP - 202
BT - Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 5 March 1991 through 7 March 1991
ER -