Cantitate/Preț
Produs

Algorithms for Sparsity-Constrained Optimization: Springer Theses, cartea 261

Autor Sohail Bahmani
en Limba Engleză Hardback – 18 oct 2013
This thesis demonstrates techniques that provide faster and more accurate solutions to a variety of problems in machine learning and signal processing. The author proposes a "greedy" algorithm, deriving sparse solutions with guarantees of optimality. The use of this algorithm removes many of the inaccuracies that occurred with the use of previous models.
Citește tot Restrânge

Toate formatele și edițiile

Toate formatele și edițiile Preț Express
Paperback (1) 88724 lei  6-8 săpt.
  Springer International Publishing – 23 aug 2016 88724 lei  6-8 săpt.
Hardback (1) 89354 lei  6-8 săpt.
  Springer International Publishing – 18 oct 2013 89354 lei  6-8 săpt.

Din seria Springer Theses

Preț: 89354 lei

Preț vechi: 108968 lei
-18% Nou

Puncte Express: 1340

Preț estimativ în valută:
17112 18518$ 14265£

Carte tipărită la comandă

Livrare economică 09-23 decembrie

Preluare comenzi: 021 569.72.76

Specificații

ISBN-13: 9783319018805
ISBN-10: 3319018809
Pagini: 154
Ilustrații: XXI, 107 p. 13 illus., 12 illus. in color.
Dimensiuni: 155 x 235 x 15 mm
Greutate: 0.39 kg
Ediția:2014
Editura: Springer International Publishing
Colecția Springer
Seria Springer Theses

Locul publicării:Cham, Switzerland

Public țintă

Research

Cuprins

Introduction.- Preliminaries.- Sparsity-Constrained Optimization.- Background.- 1-bit Compressed Sensing.- Estimation Under Model-Based Sparsity.- Projected Gradient Descent for `p-constrained Least Squares.- Conclusion and Future Work.

Notă biografică

Dr. Bahmani completed his thesis at Carnegie Mellon University and is currently employed by the Georgia Institute of Technology.

Textul de pe ultima copertă

This thesis demonstrates techniques that provide faster and more accurate solutions to a variety of problems in machine learning and signal processing. The author proposes a"greedy" algorithm, deriving sparse solutions with guarantees of optimality. The use of this algorithm removes many of the inaccuracies that occurred with the use of previous models.

Caracteristici

Nominated by Carnegie Mellon University as an outstanding Ph.D. thesis Provides an new direction of research into problems of extracting structure from data Advances the science of structure discovery through sparsity Includes supplementary material: sn.pub/extras