Adaptive Wind Driven Optimization Trained Artificial Neural Networks

TL;DR

This paper introduces the Adaptive Wind Driven Optimization (AWDO), a nature-inspired metaheuristic, for training neural networks, demonstrating its effectiveness on digit classification and discussing its potential in deep learning.

Contribution

The paper presents a novel metaheuristic optimization method, AWDO, for neural network training, with initial application results and future research directions in deep learning.

Findings

AWDO effectively trains neural networks on MNIST.

Compared to steepest descent, AWDO shows interesting behavior.

Future work includes implementing AWDO in deep neural networks.

Abstract

This paper presents the application of a newly developed nature-inspired metaheuristic optimization method, namely the Adaptive Wind Driven Optimization (AWDO), to the training of feedforward artificial neural networks (NN) and presents a discussion into the future research of AWDO implementation in Deep Learning (DL). Application example of digit classification with MNIST dataset reveals interesting behavior of the derivative-free AWDO method compared to steepest descent method where results and future work on the implementation of AWDO in deep neural networks are discussed.