Quantized Neural Modeling: Hybrid Quantized Architecture in Elman Networks

Authors:
Penghua Li;Yi Chai;Qingyu Xiong
Affiliations:
State Key Laboratory of Power Transmission Equipment and System Security and New Technology, College of Automation, Chongqing University, Chongqing, People's Republic of China 400044;State Key Laboratory of Power Transmission Equipment and System Security and New Technology, College of Automation, Chongqing University, Chongqing, People's Republic of China 400044;School of Software Engineering, Chongqing University, Chongqing, People's Republic of China 400044
Venue:
Neural Processing Letters
Year:
2013

Citing 17
Cited 0

On temporal generalization of simple recurrent networks

Neural Networks
Quantum associative memory

Information Sciences—Informatics and Computer Science: An International Journal
Image Compression by Layered Quantum Neural Networks

Neural Processing Letters
Recurrent neural networks with small weights implement definite memory machines

Neural Computation
An Examination of Qubit Neural Network in Controlling an Inverted Pendulum

Neural Processing Letters
Elman topology with sigma-pi units: An application to the modeling of verbal hallucinations in schizophrenia

Neural Networks
Modeling word perception using the Elman network

Neurocomputing
Neural networks letter: Quantum inspired PSO for the optimization of simultaneous recurrent neural networks as MIMO learning systems

Neural Networks
On the weight convergence of Elman networks

IEEE Transactions on Neural Networks
Chaotic time series prediction with residual analysis method using hybrid Elman-NARX neural networks

Neurocomputing
A new recurrent neural-network architecture for visual pattern recognition

IEEE Transactions on Neural Networks
Quantum neural networks (QNNs): inherently fuzzy feedforward neural networks

IEEE Transactions on Neural Networks
Chaotifying linear Elman networks

IEEE Transactions on Neural Networks
Predicting drug dissolution profiles with an ensemble of boosted neural networks: a time series approach

IEEE Transactions on Neural Networks
Robust Neural Network Tracking Controller Using Simultaneous Perturbation Stochastic Approximation

IEEE Transactions on Neural Networks
Robust Adaptive Gradient-Descent Training Algorithm for Recurrent Neural Networks in Discrete Time Domain

IEEE Transactions on Neural Networks
On the computational power of Elman-style recurrent networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a novel neural network model with hybrid quantized architecture to improve the performance of the conventional Elman networks. The quantum gate technique is introduced for solving the pattern mismatch between the inputs stream and one-time-delay state feedback. A quantized back-propagation training algorithm with an adaptive dead zone scheme is developed for providing an optimal or suboptimal tradeoff between the convergence speed and the generalization performance. Furthermore, the effectiveness of the new real time learning algorithm is demonstrated by proving the quantum gate parameter convergence based on Lyapunov method. The numerical experiments are carried out to demonstrate the accuracy of the theoretical results.