Search

Now showing items 1-10 of 24

Computational Capabilities of Recurrent NARX Neural Networks

Siegelmann, Hava T.; Horne, Bill G.; Giles, C. Lee (1998-10-15)

Recently, fully connected recurrent neural networks have been proven to be computationally rich --- at least as powerful as Turing machines. This work focuses on another network which is popular in control applications and ...

The Neural Network Pushdown Automaton: Model, Stack and Learning Simulations

Sun, G.Z.; Giles, C. Lee; Chen, H.H.; Lee, Y.C. (1998-10-15)

In order for neural networks to learn complex languages or grammars, they must have sufficient computational power or resources to recognize or generate such languages. Though many approaches have been discussed, one ...

Using Recurrent Neural Networks to Learn the Structure of Interconnection Networks

Goudreau, Mark W.; Giles, C. Lee (1998-10-15)

A modified Recurrent Neural Network (RNN) is used to learn a Self-Routing Interconnection Network (SRIN) from a set of routing examples. The RNN is modified so that it has several distinct initial states. This is ...

Extraction of Rules from Discrete-Time Recurrent Neural Networks

Omlin, Christian W.; Giles, C. Lee (1998-10-15)

The extraction of symbolic knowledge from trained neural networks and the direct encoding of (partial) knowledge into networks prior to training are important issues. They allow the exchange of information between symbolic and ...

Face Recognition: A Hybrid Neural Network Approach

Lawrence, Steve; Giles, C. Lee; Tsoi, Ah Chung; Back, Andrew D. (1998-10-15)

Faces represent complex, multidimensional, meaningful visual stimuli and developing a computational model for face recognition is difficult. We present a hybrid neural network solution which compares favorably with other ...

How Embedded Memory in Recurrent Neural Network Architectures Helps Learning Long-term Dependencies

Lin, Tsungnan; Horne, Bill G.; Giles, C. Lee (1998-10-15)

Learning long-term temporal dependencies with recurrent neural networks can be a difficult problem. It has recently been shown that a class of recurrent neural networks called NARX networks perform much better than ...

Product Unit Learning

Leerink, Laurens R.; Giles, C. Lee; Horne, Bill G.; Jabri, Marwan A. (1998-10-15)

Product units provide a method of automatically learning the higher-order input combinations required for the efficient synthesis of Boolean logic functions by neural networks. Product units also have a higher information ...

Neural Learning of Chaotic Dynamics: The Error Propagation Algorithm

Bakker, Rembrandt; Schouten, Jaap C.; Bleek, Cor M. van den; Giles, C. Lee (1998-10-15)

An algorithm is introduced that trains a neural network to identify chaotic dynamics from a single measured time-series. The algorithm has four special features: 1. The state of the system is extracted from the time-series ...

Learning a Class of Large Finite State Machines with a Recurrent Neural Network

Giles, C. Lee; Horne, Bill G.; Lin, T. (1998-10-15)

One of the issues in any learning model is how it scales with problem size. Neural networks have not been immune to scaling issues. We show that a dynamically-driven discrete-time recurrent network (DRNN) can learn rather ...

Fixed Points in Two--Neuron Discrete Time Recurrent Networks: Stability and Bifurcation Considerations

Tino, Peter; Horne, Bill G.; Giles, C. Lee (1998-10-15)

The position, number and stability types of fixed points of a two--neuron recurrent network with nonzero weights are investigated. Using simple geometrical arguments in the space of derivatives of the sigmoid transfer function ...