Abstract
In this paper, we propose a new type of recurrent neural-network architecture, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units. The proposed recurrent neural network differs from Jordan's and Elman's recurrent neural networks with respect to function and architecture, because it has been originally extended from being a mere multilayer feedforward neural network, to improve discrimination and generalization powers. We also prove the convergence properties of learning algorithm in the proposed recurrent neural network, and analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeric database of Concordia University, Montreal, Canada. Experimental results have confirmed that the proposed recurrent neural network improves discrimination and generalization powers in the recognition of visual patterns.
| Original language | English |
|---|---|
| Pages (from-to) | 331-340 |
| Number of pages | 10 |
| Journal | IEEE Transactions on Neural Networks |
| Volume | 8 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 1997 Dec 1 |
Fingerprint
Keywords
- Convergence properties
- Recurrent neural network
- Visual pattern recognition
ASJC Scopus subject areas
- Artificial Intelligence
- Computational Theory and Mathematics
- Hardware and Architecture
- Control and Systems Engineering
- Electrical and Electronic Engineering
- Theoretical Computer Science
Cite this
A new recurrent neural-network architecture for visual pattern recognition. / Lee, Seong Whan; Song, Hee Heon.
In: IEEE Transactions on Neural Networks, Vol. 8, No. 2, 01.12.1997, p. 331-340.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A new recurrent neural-network architecture for visual pattern recognition
AU - Lee, Seong Whan
AU - Song, Hee Heon
PY - 1997/12/1
Y1 - 1997/12/1
N2 - In this paper, we propose a new type of recurrent neural-network architecture, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units. The proposed recurrent neural network differs from Jordan's and Elman's recurrent neural networks with respect to function and architecture, because it has been originally extended from being a mere multilayer feedforward neural network, to improve discrimination and generalization powers. We also prove the convergence properties of learning algorithm in the proposed recurrent neural network, and analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeric database of Concordia University, Montreal, Canada. Experimental results have confirmed that the proposed recurrent neural network improves discrimination and generalization powers in the recognition of visual patterns.
AB - In this paper, we propose a new type of recurrent neural-network architecture, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units. The proposed recurrent neural network differs from Jordan's and Elman's recurrent neural networks with respect to function and architecture, because it has been originally extended from being a mere multilayer feedforward neural network, to improve discrimination and generalization powers. We also prove the convergence properties of learning algorithm in the proposed recurrent neural network, and analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeric database of Concordia University, Montreal, Canada. Experimental results have confirmed that the proposed recurrent neural network improves discrimination and generalization powers in the recognition of visual patterns.
KW - Convergence properties
KW - Recurrent neural network
KW - Visual pattern recognition
UR - http://www.scopus.com/inward/record.url?scp=0031095587&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031095587&partnerID=8YFLogxK
U2 - 10.1109/72.557671
DO - 10.1109/72.557671
M3 - Article
C2 - 18255636
AN - SCOPUS:0031095587
VL - 8
SP - 331
EP - 340
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
SN - 2162-237X
IS - 2
ER -