Fastest learning in small world neural networks
D. Simard, L. Nadeau, H. Kröger
Abstract
We investigate supervised learning in neural networks. We consider a multi-layered feed-forward network with back propagation. We find that the network of small-world connectivity reduces the learning error and learning time when compared to the networks of regular or random connectivity. Our study has potential applications in the domain of data-mining, image processing, speech recognition, and pattern recognition.
Create a lesson
Related papers
The Motile-Units model: Interacting spins model of cell polarization and motility
Jonathan E. Ron, Nir S. Gov
Limits of Inferring Parametric Response from Single-Condition Trajectories inStochastic Reaction Networks
Quentin Thommen
Multiflagellarity facilitates bacterial upstream motility
Ran Tao, Nathaniel C. Esteves, Wanho Lee et al.
Protein eXplosion Imaging (PXI): Protein Structures from Laser-Driven Explosions
Alfredo Bellisario, Tomas André, Carl Caleman et al.
Multiscale retinal flow on a spherical cap of varying aperture
Chang Lin, Zilong Song, Bob Eisenberg et al.
Double-well potentials and crucial estimations in nonlinear dynamics of microtubules
Rama Gupta, Nicolina Pop, Dragana Ranković et al.