Using Metaheuristics for Hyper-Parameter Optimization of Convolutional Neural Networks
Victoria Bibaeva · 2018
Convolutional neural networks (CNNs) have attracted researchers' increasing attention for almost three decades now, achieving superior results in such domains as computer vision, signal processing etc. Their success can be mainly attributed to a specific network architecture, which is conceived by assigning values to a large number of hyper-parameters, each influencing the resulting error rate. Yet a search for good hyper-parameter values is a challenging task, being usually done manually and taking a considerable amount of work. This paper is dedicated to the problem of designing automated hyper-parameter search algorithms for convolutional architectures. We propose two algorithms based on such meta-heuristics as evolutionary computation and local search. To our knowledge, they have never been applied to the case of CNN architectures before. Using image recognition datasets, we compare the algorithms and show that they can produce CNNs with nearly state of the art performance without any user interference, saving much tedious effort.