arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.05979cs.LGcs.AIcs.NEstat.ML
收藏

优化深度神经网络架构:基于禁忌搜索的方法

Optimizing Deep Neural Network Architecture: A Tabu Search Based Approach

Jamia Millia Islamia(贾米亚·米利亚·伊斯兰亚大学)

Tarun Kumar Gupta, Khalid Raza

摘要:

前馈神经网络(FNN)的性能完全取决于网络结构和训练算法的选择。FNN架构可以使用几个参数进行调整,例如隐藏层的数量,每个隐藏层的隐藏神经元数量以及层之间的连接数量。这些体系结构属性的组合可能是指数型的,这可能是人工无法管理的,所以它需要一个算法,可以自动设计一个最优的体系结构,具有较高的泛化能力。许多优化算法已被用于FNN结构的确定。本文提出了一种新的方法,它可以工作的模糊神经网络的隐层和各自的神经元的估计。结合禁忌搜索(TS)和梯度下降与动量反向传播(GDM)训练算法的优点,演示了禁忌搜索如何基于最小测试误差标准从填充的体系结构中自动选择最佳体系结构。所提出的方法已被测试的四个不同大小的分类基准数据集。

英文摘要:

The performance of Feedforward neural network (FNN) fully de-pends upon the selection of architecture and training algorithm. FNN architecture can be tweaked using several parameters, such as the number of hidden layers, number of hidden neurons at each hidden layer and number of connections between layers. There may be exponential combinations for these architectural attributes which may be unmanageable manually, so it requires an algorithm which can automatically design an optimal architecture with high generalization ability. Numerous optimization algorithms have been utilized for FNN architecture determination. This paper proposes a new methodology which can work on the estimation of hidden layers and their respective neurons for FNN. This work combines the advantages of Tabu search (TS) and Gradient descent with momentum backpropagation (GDM) training algorithm to demonstrate how Tabu search can automatically select the best architecture from the populated architectures based on minimum testing error criteria. The proposed approach has been tested on four classification benchmark dataset of different size.

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。

↑