arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.00393cs.LGstat.ML
收藏

一个强大的神经网络能成为一个较弱的神经网络的老师吗?

Can a powerful neural network be a teacher for a weaker neural network?

University of Insubria(因苏布里亚大学)

Nicola Landro, Ignazio Gallo, Riccardo La Grassa

摘要:

迁移学习技术被广泛用于在一种情况下学习并将其应用于另一种情况,即将获得的知识和技能应用于新情况的能力。但是,有没有可能将学习从深度神经网络转移到较弱的神经网络?是否有可能使用更强大的神经网络获得的知识来改善弱神经网络的性能?在这项工作中,在弱网络的训练过程中,我们添加了一个损失函数,该函数可以最小化先前从强神经网络学习的特征与弱网络必须尝试学习的特征之间的距离。为了证明我们的方法的有效性和鲁棒性,我们使用三个已知的数据集进行了大量的实验,并证明了弱神经网络可以提高其性能,如果它的学习过程是由一个更强大的神经网络驱动。

英文摘要:

The transfer learning technique is widely used to learning in one context and applying it to another, i.e. the capacity to apply acquired knowledge and skills to new situations. But is it possible to transfer the learning from a deep neural network to a weaker neural network? Is it possible to improve the performance of a weak neural network using the knowledge acquired by a more powerful neural network? In this work, during the training process of a weak network, we add a loss function that minimizes the distance between the features previously learned from a strong neural network with the features that the weak network must try to learn. To demonstrate the effectiveness and robustness of our approach, we conducted a large number of experiments using three known datasets and demonstrated that a weak neural network can increase its performance if its learning process is driven by a more powerful neural network.

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。

↑