This study investigates the application of Bayesian Optimization (BO) for the hyperparameter tuning of neural networks, specifically targeting the enhancement of Convolutional Neural Networks (CNN) for image classification tasks. Bayesian Optimization is a derivative-free global optimization method suitable for expensive black-box functions with continuous inputs and limited evaluation budgets. The BO algorithm leverages Gaussian Process regression and acquisition functions like Upper Confidence Bound (UCB) and Expected Improvement (EI) to identify optimal configurations effectively. Using the Ax and BOTorch frameworks, this work demonstrates the efficiency of BO in reducing the number of hyperparameter tuning trials while achieving competitive model performance. Experimental outcomes reveal that BO effectively balances exploration and exploitation, converging rapidly towards optimal settings for CNN architectures. This approach underlines the potential of BO in automating neural network tuning, contributing to improved accuracy and computational efficiency in machine learning pipelines.

翻译：本研究探讨了贝叶斯优化（BO）在神经网络超参数调优中的应用，特别针对提升卷积神经网络（CNN）在图像分类任务中的性能。贝叶斯优化是一种无导数的全局优化方法，适用于具有连续输入和有限评估预算的昂贵黑箱函数。该算法利用高斯过程回归以及上置信界（UCB）和期望改进（EI）等采集函数，以有效识别最优配置。通过使用Ax和BOTorch框架，本工作证明了BO在减少超参数调优试验次数的同时，能够实现具有竞争力的模型性能。实验结果表明，BO能有效平衡探索与利用，快速收敛至CNN架构的最优设置。该方法凸显了BO在自动化神经网络调优中的潜力，有助于提升机器学习流程的准确性与计算效率。