Nonlinear Algebra In An Acorn: With Applications To Deep Learning

With Applications to Deep Learning

Omschrijving

A simple algorithm for solving a set of nonlinear equations by matrix algebra has been discovered recently - first by transforming them into an equivalent matrix equation and then finding the solution analytically in terms of the inverse matrix of this equation. With this newly developed ACORN (Adaptive Constrained Optimal Robust Nonlinear) algorithm, it is possible to minimize the objective function [constructed from the functions in the nonlinear set of equations] without computing its derivatives. This book will present the details of ACORN algorithm and how it is used to solve large scale nonlinear equations with an innovative approach ACORN Magic [minimization algorithms gathered in a cloud]. The ultimate motivation of this work is its application to optimization. In recent years, with the advances in big-data, optimization becomes an even more powerful tool in knowledge discovery. ACORN Magic is the perfect choice in this kind of application because of that fact that it is fast, robust and simple enough to be embedded in any type of machine learning program.
Gratis verzending vanaf
€ 19,95 binnen Nederland
Schrijver
Lee, Martin J (Stanford Univ & Tai Chi Cultural Center, Tsang, Ken Kang Too (Beijing Normal Univ-hong Kong Baptist Univ United International College
Titel
Nonlinear Algebra In An Acorn: With Applications To Deep Learning
Uitgever
World Scientific Publishing Co Pte Ltd
Jaar
2018
Taal
Engels
Pagina's
92
Gewicht
345 gr
EAN
9789813271517
Afmetingen
229 x 159 x 13 mm
Bindwijze
Hardback

U ontvangt bij ons altijd de laatste druk!


Rubrieken

Boekstra