A Better Activation Function for Artificial Neural Networks

Simple item page
dc.contributor.authorElliott, David L.en_US
dc.contributor.departmentISRen_US
dc.date.accessioned2007-05-23T09:53:23Z
dc.date.available2007-05-23T09:53:23Z
dc.date.issued1993en_US
dc.description.abstractAn activation function, possibly new, is proposed for use in digital simulation of artificial neural networks, on the ground that the computational operation count for this function is much smaller than for those employing exponentials and it satisfies a simple differential equation generalizing the logistic equation.en_US
dc.format.extent132906 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/5355
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; TR 1993-8en_US
dc.subjectneural networksen_US
dc.subjectnonlinear systemsen_US
dc.subjectCommunication en_US
dc.subjectSignal Processing Systemsen_US
dc.titleA Better Activation Function for Artificial Neural Networksen_US
dc.typeTechnical Reporten_US

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
TR_93-8.pdf
Size:
129.79 KB
Format:
Adobe Portable Document Format
Download

Collections

Institute for Systems Research Technical Reports