About this document

LHABC: Enhanced Neural Network Training by Vishnu Deepak is a document available to read on EtoBox.

This document proposes two new algorithms based on modifications to the original Artificial Bee Colony algorithm to train neural networks. The first algorithm is called Neural-Modified ABC (NMABC) and employs neural network-appropriate initialization and linear search space expansion. The second is called Layered-Hybrid ABC (LHABC) and incorporates stochastic gradient descent into the employed phase of the bees for faster convergence. Both algorithms are tested on three benchmark classification datasets and

Author

Vishnu Deepak

Language

EN