In this study, we model a CNN hyper-parameter optimization problem as a bi-criteria optimization problem, where the first objective being the classification accuracy and the second objective being the computational complexity which is measured in terms of the number of floating point operations. For this bi-criteria optimization problem, we develop a Multi-Objective Simulated Annealing (MOSA) algorithm for obtaining high-quality solutions in terms of both objectives. CIFAR-10 is selected as the benchmark dataset, and the MOSA trade-off fronts obtained for this dataset are compared to the fronts generated by a single-objective Simulated Annealing (SA) algorithm with respect to several front evaluation metrics such as generational distance, spacing and spread. The comparison results suggest that the MOSA algorithm is able to search the objective space more effectively than the SA method. For each of these methods, some front solutions are selected for longer training in order to see their actual performance on the original test set. Again, the results state that the MOSA performs better than the SA under multi-objective setting. The performance of the MOSA configurations are also compared to other search generated and human designed state-of-the-art architectures. It is shown that the network configurations generated by the MOSA are not dominated by those architectures, and the proposed method can be of great use when the computational complexity is as important as the test accuracy.

中文翻译：

---

卷积神经网络中超参数优化的多目标模拟退火

在这项研究中，我们将CNN超参数优化问题建模为双准则优化问题，其中第一个目标是分类精度，第二个目标是根据浮点运算次数来衡量的计算复杂度。针对此双准则优化问题，我们开发了一种多目标模拟退火（MOSA）算法，以在两个目标方面获得高质量的解决方案。选择CIFAR-10作为基准数据集，并将针对该数据集获得的MOSA权衡前沿与通过单目标模拟退火（SA）算法针对若干前沿评估指标（例如世代距离，间距和传播。比较结果表明，与SA方法相比，MOSA算法能够更有效地搜索目标空间。对于每种方法，都选择了一些前端解决方案以进行更长的培训，以便在原始测试集上查看其实际性能。同样，结果表明，在多目标设置下，MOSA的性能优于SA。MOSA配置的性能也与其他搜索生成和人工设计的最新体系结构进行了比较。结果表明，由MOSA生成的网络配置不受那些体系结构支配，并且当计算复杂度与测试精度同样重要时，所提出的方法可能会很有用。选择一些前端解决方案进行较长时间的培训，以便在原始测试集中查看其实际性能。同样，结果表明，在多目标设置下，MOSA的性能优于SA。MOSA配置的性能也与其他搜索生成和人工设计的最新体系结构进行了比较。结果表明，由MOSA生成的网络配置不受那些体系结构支配，并且当计算复杂度与测试精度同样重要时，所提出的方法可能会很有用。选择一些前端解决方案进行较长时间的培训，以便在原始测试集中查看其实际性能。同样，结果表明，在多目标设置下，MOSA的性能优于SA。MOSA配置的性能也与其他搜索生成和人工设计的最新体系结构进行了比较。结果表明，由MOSA生成的网络配置不受那些体系结构支配，并且当计算复杂度与测试精度同样重要时，所提出的方法可能会很有用。MOSA配置的性能也与其他搜索生成和人工设计的最新体系结构进行了比较。结果表明，由MOSA生成的网络配置不受那些体系结构支配，并且当计算复杂度与测试精度同样重要时，所提出的方法可能会很有用。MOSA配置的性能也与其他搜索生成和人工设计的最新体系结构进行了比较。结果表明，由MOSA生成的网络配置不受那些体系结构支配，并且当计算复杂度与测试精度同样重要时，所提出的方法可能会很有用。