Results 281 to 290 of about 401,900 (340)

Belief Propagation, Dykstra's Algorithm, and Iterated Information Projections

IEEE Transactions on Information Theory, 2010
Belief propagation is shown to be an instance of a hybrid between two projection algorithms in the convex programming literature: Dykstra's algorithm with cyclic Bregman projections and an alternating Bregman projections algorithm. Via this connection, new results concerning the convergence and performance of belief propagation can be proven by ...
John MacLaren Walsh, Phillip A. Regalia
openaire   +1 more source

Iterative Project Quasi-Newton Algorithm for Training RBM

Proceedings of the AAAI Conference on Artificial Intelligence, 2016
The restricted Boltzmann machine (RBM) has been used as building blocks for many successful deep learning models, e.g., deep belief networks (DBN) and deep Boltzmann machine (DBM) etc. The training of RBM can be extremely slow in pathological regions.
Shuai Mi, Xiaozhao Zhao, Yuexian Hou, Peng Zhang, Wenjie Li, Dawei Song   +5 more
openaire   +1 more source

Strong convergence of an iterative algorithm involving nonlinear mappings of nonexpansive and accretive type

Optimization, 2018
In this paper, a new iterative method for finding the projection onto the intersection of two closed convex sets in the framework of Banach spaces is presented. It is a viscosity approximation method which produces a strongly convergent sequence.
X. Qin, S. Cho, Lin Wang
semanticscholar   +1 more source

Performance evaluation of iterative tomography algorithms for incomplete projection data

Applied Optics, 2004
Projection data obtained through optical techniques for tomographic measurements, such as interferometry for refractive-index-based measurements, are often incomplete. This is due to limitations in the optical system, data storage, and alignment and vignette issues.
Debasish, Mishra, Jon P, Longtin, Raman P, Singh, Vishwanath, Prasad   +3 more
openaire   +2 more sources

Iterative Subgradient Projection Algorithm

2016
In this chapter we study convergence of iterative subgradient projection algorithms for solving convex feasibility problems in a general Hilbert space. Our goal is to obtain an approximate solution of the problem in the presence of computational errors.
openaire   +1 more source

Projective iterative hard thresholding algorithm for sparse signal recovery

2015 International Conference on Estimation, Detection and Information Fusion (ICEDIF), 2015
Recovering sparse signals from a few linear measurements is attracting growing attention. Bsides sparsity, the signals usually are nonnegative, nonpositive or restricted in some domain. This paper proposes an algorithm for recovering the sparse signal with some certain property on learning the sparsity.
null Zhongao Zhou, null Tao Sun, null Lizhi Cheng   +2 more
openaire   +1 more source

A projection iterative algorithm for strong vector equilibrium problem

Optimization, 2014
In this paper, iterative algorithm for strong vector equilibrium problem (SVEP) is studied. Firstly, an auxiliary problem for SVEP is introduced and the relationships between these two problems are discussed. Then, based on the auxiliary problem, a projection iterative algorithm for SVEP is proposed.
San-hua Wang, Qiu-ying Li
openaire   +1 more source

Iterative learning control algorithm based on newton-projection method

Proceeding of the 11th World Congress on Intelligent Control and Automation, 2014
The iterative learning control algorithm based on Newton-Projection method for nonlinear dynamic system is proposed. Introduced projection method to iterative learning control problem, we construct the orthonormal basis of the control space. The output tracking problem is transformed into the problem of nonlinear equations in the finite dimension ...
Jingli Kang, Yaoguo Li
openaire   +1 more source

Convergence of Picard’s iteration using projection algorithm for noncyclic contractions

Indagationes Mathematicae, 2019
This paper deals with some of the conditions for the convergence of Picard's iteration for non-cyclic contractions using a projection algorithm in uniformly convex Banach spaces. The author also discusses the existence of common best proximity pairs for a couple of non-cyclical mappings. Some examples are given to illustrate the main conclusions.
openaire   +2 more sources

Non-iterative conductivity reconstruction algorithm using projected current density in MREIT

Physics in Medicine and Biology, 2008
Magnetic resonance electrical impedance tomography (MREIT) is to visualize the current density and the conductivity distribution in an electrical object Omega using the measured magnetic flux data by an MRI scanner. MREIT uses only one component B(z) of the magnetic flux density B = (B(x), B(y), B(z)) generated by an injected electrical current into ...
Hyun Soo, Nam, Chunjae, Park, Oh In, Kwon   +2 more
openaire   +2 more sources