Learning multilayer perceptrons efficiently
C. Bunzmann, M. Biehl, R. Urbanczik
Abstract
A learning algorithm for multilayer perceptrons is presented which is based on finding the principal components of a correlation matrix computed from the example inputs and their target outputs. For large networks our procedure needs far fewer examples to achieve good generalization than traditional on-line algorithms.
Create a lesson
Related papers
Coupling spherical p-spin systems
Riccardo Cipolloni, Leticia F. Cugliandolo
Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory
Yuto Sakurai, Takeaki Shimokawa, Kazunori Iwata et al.
Latent kinetic Ising models of neural spike trains
Davide Ghio, David Saad
Nonlocal Magic across the Many-Body Localization Crossover
Shan-Zhong Li, Zhi Li
Statistical levels and spatial modes of Fock-space heterogeneity in many-body localization crossovers
Yu-Jing Liu, Chen Cheng
Disorder-Tailored Delocalization
Yeongjun Kim, Supriyo Ghosh, Sergej Flach