Abstract:
Intelligent neural network processing of various signals with continuous learning is of great scientific and practical interest. For such processing, along with other solutions, streaming pulse recurrent neural networks (RNNs) with advanced functionality are used. However, for these RNNs, the issues of ensuring their stable operation have not been studied in many respects. The goal is to increase the stability of streaming pulse RNNs by developing new methods of intelligent signal processing with continuous learning. For this purpose, the capabilities of these RNNs are clarified and approaches to ensuring their stability during training and signal generation are analyzed. The streaming RNN is formalized as a relatively finite operational automaton. A new method for stable intelligent signal processing by an improved RNN with continuous learning is proposed. Schemes for solving various intelligent problems of analysis and synthesis by the proposed method are considered. The modeling results are presented, confirming the operability of the proposed method and the possibility of increasing the stability of RNNs during continuous training and signal generation. The achievability of a stable balance between memorized and gradually forgotten information in the RNN with prompt adaptation to changing external conditions is shown.
Keywords:neural network, intelligence, stability, continuous learning, signal generation.
Fulltext:
PDF file (2752 kB)