Jump to content

George Cybenko

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by 98.29.217.98 (talk) at 17:52, 4 January 2021. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

George Cybenko is the Dorothy and Walter Gramm Professor of Engineering at Dartmouth and a fellow of the IEEE and SIAM.[1]

Education

Cybenko obtained his BA in mathematics from the University of Toronto and received his PhD from Princeton in applied mathematics of electrical and computer engineering in 1978.

Work

Cybenko has served as an advisor for the Defense Science Board and several other government panels and is the founding editor-in-chief of the IEEE Security & Privacy magazine. His current research interests are distributed information, control systems, and signal processing, with a focus on applications to security and infrastructure protection. He is known for proving the universal approximation theorem for artificial neural networks with sigmoid activation functions.[2]

References

  1. ^ Princeton EE alumni profiles
  2. ^ Cybenko, G. (1989) "Approximations by superpositions of sigmoidal functions", Mathematics of Control, Signals, and Systems, 2(4), 303–314. doi:10.1007/BF02551274