BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Algebraic function based Banach space valued ordinary and fraction
 al neural network approximations - George  Anastassiou (University of Memp
 his)
DTSTART:20220228T181500Z
DTEND:20220228T191500Z
UID:TALK170030@talks.cam.ac.uk
DESCRIPTION:Here we research the univariate quantitative approximation\, o
 rdinary\nand fractional\, of Banach space valued continuous functions on a
  compact\ninterval or all the real line by quasi-interpolation Banach spac
 e valued\nneural network operators. These approximations are derived by es
 tab-\nlishing Jackson type inequalities involving the modulus of continuit
 y of\nthe engaged function or its Banach space valued high order derivativ
 e of\nfractional derivatives. Our operators are defined by using a density
  func-\ntion generated by an algebraic sigmoid function. The approximation
 s are\npointwise and of the uniform norm. The related Banach space valued\
 nfeed-forward neural networks are with one hidden layer.
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR