Many studies on the associative memory networks deal with the inverse problem: find a connecting weight matrix such that the network has equilibrium attractors at the given points. In this paper, another kind of inverse problem is investigated: find a weight matrix such that the network has periodic attractors with the given output wave forms.One solution for this problem is given by the Adaptive Neural Oscillator learning. The A N 0 is a recurrent network of continuous-time continuousoutput model neurons. Modified back-propagation learning is performed so as to make the output wave form as close as possible to the external input wave form. If the output wave form has become sufficiently similar to the input wave form, by making a feedback of the output wave form instead of the external input, the network continues an autonomous oscillation with a wave form similar to the previously given external input wave form.By combining the A N 0 lerning with the scheme of the associative memory network, multiple oscillatory wave forms can be stored in one neural network, and each one of them can be selectively regenerated with the initial state of the network.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.