Neural network architectures found by sophistic search algorithms achieve strikingly good test performance, surpassing most human-crafted network models by significant margins. Although computationally efficient, their design is often very complex, impairing execution speed. Additionally, finding models outside of the search space is not possible by design. While our space is still limited, we implement undiscoverable expert knowledge into the economic search algorithm Efficient Neural Architecture Search (ENAS), guided by the design principles and architecture of ShuffleNet V2. While maintaining baseline-like 2.85% test error on CIFAR-10, our ShuffleNASNets are significantly less complex, require fewer parameters, and are two times faster than the ENAS baseline in a classification task. These models also scale well to a low parameter space, achieving less than 5% test error with little regularization and only 236K parameters.

翻译：光速搜索算法所发现的神经网络结构的测试性能惊人地好,大大超过大多数人造网络模型的显著边距。 虽然计算效率很高,但其设计往往非常复杂,损害执行速度。 此外,在搜索空间之外寻找模型无法通过设计实现。虽然我们的空间仍然有限,但我们在ShuffleNet V2的设计原则和结构指导下,将无法发现的专业知识应用到经济搜索算法高效神经结构搜索(ENAS ) 。 我们的ShuffleNASNets在CIFAR-10上维持了类似2.85%的基线测试错误,同时我们的ShuffleNASnets在分类任务中也远不那么复杂,需要更少的参数,而且比ENAS基准速度快两倍。 这些模型还非常适合低参数空间,在很少规范的情况下,只达到不到5%的测试错误,只有236K参数。