Architecture search optimizes the structure of a neural network for some task instead of relying on manual authoring. However, it is slow, as each potential architecture is typically trained from scratch. In this paper we present an approach called Conceptual Expansion Neural Architecture Search (CENAS) that combines a sample-efficient, computational creativity-inspired transfer learning approach with neural architecture search. This approach finds models faster than naive architecture search via transferring existing weights to approximate the parameters of the new model. It outperforms standard transfer learning by allowing for the addition of features instead of only modifying existing features. We demonstrate that our approach outperforms standard neural architecture search and transfer learning methods in terms of efficiency, performance, and parameter counts on a variety of transfer learning tasks.
翻译:建筑搜索优化了神经网络的结构, 而不是依靠手动写作。 但是, 它很慢, 因为每个潜在结构通常都是从零开始训练的。 在本文中, 我们提出了一个名为“ 概念扩展神经结构搜索 ” ( CENAS ) 的方法, 将样本高效、 计算创新型转移学习方法与神经结构搜索结合起来。 这个方法发现模型比天真的结构搜索更快, 方法是将现有重量转换到接近新模型参数。 它通过允许添加功能而不是仅仅修改现有特征而优于标准转移学习。 我们证明, 我们的方法在效率、 性能和参数方面, 超越了标准神经结构搜索和转移学习方法, 体现在各种转移学习任务上 。