论文标题
通过替代模型来增强新颖搜索
Augmenting Novelty Search with a Surrogate Model to Engineer Meta-Diversity in Ensembles of Classifiers
论文作者
论文摘要
使用神经进化与新颖搜索相结合来促进行为多样性，能够构建高性能的合奏进行分类。但是，在搜索过程中，使用梯度下降来训练进化的体系结构可能会在计算上过于刺激。在这里，我们提出了一种通过使用替代模型来克服此限制的方法，该模型估算了在新颖性搜索中计算稀疏项所需的两个神经网络体系结构之间的行为距离。我们证明了以前的工作的速度为10倍，并在计算机视觉的三个基准数据集上显着改善了以前报告的结果-CIFAR-10，CIFAR-100和SVHN。这是由于扩展的架构搜索空间通过使用替代物来促进的。我们的方法代表了一种改进的范式，用于通过对相同有限资源进行明确搜索多样性的明确搜索来实现学习算法的水平缩放。
Using Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification. However, using gradient descent to train evolved architectures during the search can be computationally prohibitive. Here we propose a method to overcome this limitation by using a surrogate model which estimates the behavioural distance between two neural network architectures required to calculate the sparseness term in Novelty Search. We demonstrate a speedup of 10 times over previous work and significantly improve on previous reported results on three benchmark datasets from Computer Vision -- CIFAR-10, CIFAR-100, and SVHN. This results from the expanded architecture search space facilitated by using a surrogate. Our method represents an improved paradigm for implementing horizontal scaling of learning algorithms by making an explicit search for diversity considerably more tractable for the same bounded resources.
