A New Local Bipolar Autoassociative Memory Based on External Inputs of Discrete Recurrent Neural Networks With Time Delay
| Autor: | Xiaoqin Zeng, Chaomin Luo, Huaguang Zhang, Caigen Zhou |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
Time Factors Computer Networks and Communications Computer science Activation function 02 engineering and technology Autoassociative memory 020901 industrial engineering & automation Exponential stability Memory Artificial Intelligence Robustness (computer science) Control theory 0202 electrical engineering electronic engineering information engineering Humans Computer Simulation Artificial neural network Time delay neural network Association Learning Content-addressable memory Computer Science Applications Recurrent neural network 020201 artificial intelligence & image processing Neural Networks Computer Types of artificial neural networks Algorithms Software |
| Zdroj: | IEEE Transactions on Neural Networks and Learning Systems. 28:2479-2489 |
| ISSN: | 2162-2388 2162-237X |
| Popis: | In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|