LGMLNov 20, 2019

Adaptive Wind Driven Optimization Trained Artificial Neural Networks

arXiv:1911.08942v11 citations
Originality Synthesis-oriented
AI Analysis

This work addresses training neural networks with a derivative-free optimization method, but it appears incremental as it applies a new metaheuristic without clear broad impact.

The paper applied the Adaptive Wind Driven Optimization (AWDO) method to train feedforward neural networks, comparing it to steepest descent on the MNIST digit classification dataset, but did not report specific numerical results.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes