arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.02655cs.NEcs.LG
收藏

基于网络感知自适应的深度循环神经网络神经进化迁移学习

Neuroevolutionary Transfer Learning of Deep Recurrent Neural Networks through Network-Aware Adaptation

Rochester Institute of Technology(罗切斯特理工学院)

AbdElRahman ElSaid, Joshua Karns, Alexander Ororbia, Daniel Krutz, Zimeng Lyu, Travis Desell

摘要:

迁移学习需要采用在源数据集上训练的人工神经网络(ANN)并使其适应新的目标数据集。虽然这已经被证明是非常强大的,但它的使用通常受到架构约束的限制。以前,为了重用和适应ANN的内部权重和结构,在任务之间传输的ANN的底层拓扑必须保持基本相同,同时附加新的输出层,丢弃旧的输出层的权重。这项工作介绍了网络感知的自适应结构迁移学习(N-ASTL),在以前的努力,以消除这种限制的进步。N-ASTL利用与源网络的拓扑和权重分布相关的统计信息,以告知如何将新的输入和输出神经元集成到现有结构中。结果显示了对现有技术的改进,包括在具有挑战性的现实世界数据集中转移的能力,以及在没有转移的情况下训练的RNN的改进泛化能力。

英文摘要:

Transfer learning entails taking an artificial neural network (ANN) that is trained on a source dataset and adapting it to a new target dataset. While this has been shown to be quite powerful, its use has generally been restricted by architectural constraints. Previously, in order to reuse and adapt an ANN's internal weights and structure, the underlying topology of the ANN being transferred across tasks must remain mostly the same while a new output layer is attached, discarding the old output layer's weights. This work introduces network-aware adaptive structure transfer learning (N-ASTL), an advancement over prior efforts to remove this restriction. N-ASTL utilizes statistical information related to the source network's topology and weight distribution in order to inform how new input and output neurons are to be integrated into the existing structure. Results show improvements over prior state-of-the-art, including the ability to transfer in challenging real-world datasets not previously possible and improved generalization over RNNs trained without transfer.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑