![]() |
COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. | ![]() |
University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > Algebraic function based Banach space valued ordinary and fractional neural network approximations
![]() Algebraic function based Banach space valued ordinary and fractional neural network approximationsAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact nobody. FDE2 - Fractional differential equations Here we research the univariate quantitative approximation, ordinary and fractional, of Banach space valued continuous functions on a compact interval or all the real line by quasi-interpolation Banach space valued neural network operators. These approximations are derived by estab- lishing Jackson type inequalities involving the modulus of continuity of the engaged function or its Banach space valued high order derivative of fractional derivatives. Our operators are defined by using a density func- tion generated by an algebraic sigmoid function. The approximations are pointwise and of the uniform norm. The related Banach space valued feed-forward neural networks are with one hidden layer. This talk is part of the Isaac Newton Institute Seminar Series series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsList 1 Culture of Scientific Research SBR Graduate TalksOther talksOptimisation Training for Industry (Virtual) Pulsar Timing Arrays: The Next Window to Open on the Gravitational-Wave Universe Title: Things that go crash in the night. Tales from the inherited arrhythmia clinic. Traditional Medicine Goes Global: Pan-African Precedents, Cultural Decolonization, and Cold War Rights/Properties’ Cybernetics Revolution in Contemporary China Flavour Anomalies-Collider Interplay |