A Deep Learning Framework for Automated Transfer Learning of Neural Networks
A Deep Learning Framework for Automated Transfer Learning of Neural Networks
复制标题
用于神经网络自动迁移学习的深度学习框架
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
R. Ravi
中科院分区：
文献类型：
--
作者：
Thanasekhar Balaiah;T. Jeyadoss;S. Thirumurugan;R. Ravi
迁移学习是一种通过重用先前训练的源神经网络的权重来减少训练时间并提高性能的技术。这就提出了如何选择源网络的问题，这仍然是一个未解决的问题。在这项工作中，我们构建了一个框架，通过基于数据集分类难度的估计选择源神经网络来自动执行迁移学习。该框架将难度最接近的数据集的神经网络指定为源。该框架在7个数据集上进行了评估，即SVHN，Cifar10，Cifar100，GTSRB，MNIST，Flowers和Linnaeus5，实验结果表明，在大多数情况下，这种类型的源选择在准确性上得到了最高的提高。与从头开始训练相比，该框架为ResNet提供了6.7%的平均准确率提高，并且在某些情况下在前10个epoch内实现。
Transfer Learning is a technique that reduces the time taken for training and improves performance by reusing the weights of a previously trained source neural network. This poses a question of how the source network must be chosen, which is still an unsolved problem. In this work, we have built a framework that automatically performs transfer learning by selecting the source neural network based on an estimate of dataset classification difficulty. The framework designates the neural network of the dataset that is closest in difficulty as the source. The framework is evaluated on 7 datasets namely SVHN, Cifar10, Cifar100, GTSRB, MNIST, Flowers and Linnaeus5, and experimental results suggest that in most cases this type of source selection gives the highest improvement in accuracy. The framework provides an average improvement in accuracy of 6.7% for ResNet than when training from scratch, and achieves it within the first 10 epochs in some cases.