Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
The Recursive Neural Network Don Hush, Chaouki Abdallah, and Bill Horne
 

Summary: The Recursive Neural Network
Don Hush, Chaouki Abdallah, and Bill Horne
Department of Electrical Engineering and Computer Engineering
University of New Mexico
Albuquerque, NM, 87131 USA.
The Recursive Neural Network 2
ABSTRACT
This paper describes a special type of dynamic neural network called the Recursive
Neural Network (RNN). The RNN is a single-input single-output nonlinear dynamical
system with three subnets, a nonrecursive subnet and two recursive subnets. The nonre-
cursive subnet feeds current and previous input samples through a multi-layer perceptron
with second order input units (SOMLP) [9]. In a similar fashion the two recursive sub-
nets feed back previous output signals through SOMLPs. The outputs of the three sub-
nets are summed to form the overall network output. The purpose of this paper is to
describe the architecture of the RNN, to derive a learning algorithm for the network
based on a gradient search, and to provide some examples of its use.
The work in this paper is an extension of previous work on the RNN [10]. In previ-
ous work the RNN contained only two subnets, a nonrecursive subnet and a recursive
subnet. Here we have added a second recursive subnet. In addition, both of the subnets
in the previous RNN had linear input units. Here all three of the subnets have second

  

Source: Abdallah, Chaouki T- Electrical and Computer Engineering Department, University of New Mexico

 

Collections: Engineering