A Heuristic for Efficient Reduction in Hidden Layer Combinations For Feedforward Neural Networks

TL;DR

This paper introduces a heuristic method to efficiently reduce the number of hidden layer combinations in feedforward neural networks, significantly decreasing search time with minimal impact on performance.

Contribution

The paper proposes a novel heuristic approach for hyper-parameter search that outperforms exhaustive methods in efficiency while maintaining comparable model quality.

Findings

Significant reduction in hyper-parameter search time

Marginal differences in model evaluation metrics

Heuristic approach outperforms exhaustive search in efficiency

Abstract

In this paper, we describe the hyper-parameter search problem in the field of machine learning and present a heuristic approach in an attempt to tackle it. In most learning algorithms, a set of hyper-parameters must be determined before training commences. The choice of hyper-parameters can affect the final model's performance significantly, but yet determining a good choice of hyper-parameters is in most cases complex and consumes large amount of computing resources. In this paper, we show the differences between an exhaustive search of hyper-parameters and a heuristic search, and show that there is a significant reduction in time taken to obtain the resulting model with marginal differences in evaluation metrics when compared to the benchmark case.