Abstract
In this chapter we introduce a biologically plausible model of the neural integrator model based on recurrent neural networks. Its original features are: fixed sign synaptic weights for all the network connections; and artificial transmission delays between the units. These improvements lead to the emergence of clusters in the weight structure of the lateral inhibitory connection layer. We will demonstrate that these clusters are not an artifact of computation.We will see that this spontaneous emergence of clusters in artificial neural networks, performing a well defined physico—mathematical task (a temporal integration) is owed to computational constraints, with a restricted space of solutions. Thus information processing constraints could be a plausible factor inducing the emergence of iterated patterns in biological neural networks.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
