Poziv na predavanje na engleskom jeziku Neural Net Approximation and Estimation of Functions

Odjel za matematiku Sveučilišta Josipa Jurja Strossmayera u Osijeku organizira predavanje Neural Net Approximation and Estimation of Functions, na engleskom jeziku

NAJAVA – Predavanje će se održati u četvrtak, 12. ožujka 2015. godine s početkom u 17 sati u predavaonici broj 36 na Odjelu za matematiku Sveučilišta Josipa Jurja Strossmayera u Osijeku (Trg Ljudevita Gaja 6).

Predavanje će održati:

• Prof. Andrew Barron, Yale University, Department of Statistics, USA

S obzirom da je riječ o predavanju na engleskom jeziku, na tom jeziku objavljujemo i kratak opis predavanja:

Artificial neural networks, consisting of one or more layers of superpositions of sigmoidal ridge functions, are intended for approximation and estimation of functions of many variables. These neural nets are closely related to other statistical methods including sparse sinusoids, hinging hyperplanes, and projection pursuit regression. In this talk I review the approximation and estimation capabilities of these models as well as the computational challenges.