Local Minima of a Quadratic Binary Functional with a Quasi-Hebbian Connection Matrix

12/22/2010
by   Yakov Karandashev, et al.
0

The local minima of a quadratic functional depending on binary variables are discussed. An arbitrary connection matrix can be presented in the form of quasi-Hebbian expansion where each pattern is supplied with its own individual weight. For such matrices statistical physics methods allow one to derive an equation describing local minima of the functional. A model where only one weight differs from other ones is discussed in detail. In this case the equation can be solved analytically. The critical values of the weight, for which the energy landscape is reconstructed, are obtained. Obtained results are confirmed by computer simulations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/24/2004

Global minimization of a quadratic functional: neural network approach

The problem of finding out the global minimum of a multiextremal functio...
research
06/25/2012

Optimization of Real, Hermitian Quadratic Forms: Real, Complex Hopfield-Amari Neural Network

In this research paper, the problem of optimization of quadratic forms a...
research
11/17/2020

Optimizing parametrized quantum circuits via noise-induced breaking of symmetries

Very little is known about the cost landscape for parametrized Quantum C...
research
06/15/2020

Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 2: Experiments and Analysis

The existence of local minima for one-hidden-layer ReLU networks has bee...
research
07/18/2019

Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model

Gradient-based algorithms are effective for many machine learning tasks,...
research
11/15/2021

Axiomatic characterization of the χ^2 dissimilarity measure

We axiomatically characterize the χ^2 dissimilarity measure. To this end...
research
12/01/2021

Spurious Valleys, Spurious Minima and NP-hardness of Sparse Matrix Factorization With Fixed Support

The problem of approximating a dense matrix by a product of sparse facto...

Please sign up or login with your details

Forgot password? Click here to reset