论文标题
一个基于多源转移学习的有效进化深度学习框架，以发展深卷积神经网络
An Efficient Evolutionary Deep Learning Framework Based on Multi-source Transfer Learning to Evolve Deep Convolutional Neural Networks
论文作者
论文摘要
卷积神经网络（CNN）通过引入更复杂的拓扑结构并扩大了更深入和更广泛的CNN的能力，在多年来一直取得了更好的性能。这使得CNN的手动设计极为困难，因此CNN的自动设计已经进入了研究焦点，该研究的焦点已获得超过手动设计的CNN的CNN。但是，计算成本仍然是自动设计CNN的瓶颈。在本文中，受到转移学习的启发，提出了一个新的基于进化计算的框架，以有效地进化CNN，而不会损害分类精度。所提出的框架利用比目标域数据集更小的数据集的多源域，仅进化了一个广义的CNN块。然后，提出了一种新的堆叠方法来扩大和加深进化的块，并提出了一种网格搜索方法以找到最佳的堆叠溶液。实验结果表明，所提出的方法在不到40个GPU小时内以比15个同伴竞争对手更快地获得了良好的CNN。关于分类的准确性，提出的方法对同伴竞争对手获得了强大的竞争力，该竞争者的最佳错误率分别为CIFAR-10，CIFAR-100和SVHN数据集的最佳错误率，分别为3.46％，18.36％和1.76％。
Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely difficult, so the automated design of CNNs has come into the research spotlight, which has obtained CNNs that outperform manually-designed CNNs. However, the computational cost is still the bottleneck of automatically designing CNNs. In this paper, inspired by transfer learning, a new evolutionary computation based framework is proposed to efficiently evolve CNNs without compromising the classification accuracy. The proposed framework leverages multi-source domains, which are smaller datasets than the target domain datasets, to evolve a generalised CNN block only once. And then, a new stacking method is proposed to both widen and deepen the evolved block, and a grid search method is proposed to find optimal stacking solutions. The experimental results show the proposed method acquires good CNNs faster than 15 peer competitors within less than 40 GPU-hours. Regarding the classification accuracy, the proposed method gains its strong competitiveness against the peer competitors, which achieves the best error rates of 3.46%, 18.36% and 1.76% for the CIFAR-10, CIFAR-100 and SVHN datasets, respectively.
