arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.11397stat.MLcs.LG
收藏

NN2Poly:深度前馈人工神经网络的多项式表示

NN2Poly: A polynomial representation for deep feed-forward artificial neural networks

Universidad Carlos III de Madrid(马德里卡洛斯三世大学);Universidad Pontificia Comillas(卡米亚斯大主教大学)

Pablo Morala, Jenny Alexandra Cifuentes, Rosa E. Lillo, Iñaki Ucar

AI总结:

本文提出NN2Poly方法,利用泰勒展开和组合性质,将任意深度的全连接前馈神经网络转换为显式多项式,以提升可解释性,并通过实验验证其有效性。

摘要:

尽管神经网络的实际应用取得了巨大成功,特别是在深度学习的出现之后,其可解释性及其潜在的理论行为仍然是一个开放的研究领域。在这项工作中,我们提出了NN2Poly:一种理论方法,用于获得一个显式多项式模型,该模型能够准确表示已经训练好的全连接前馈人工神经网络(即多层感知器或MLP)。该方法扩展了文献中先前提出的一个想法,该想法仅限于单隐层网络,现在可以处理任意深度的MLP,适用于回归和分类任务。NN2Poly在每一层对激活函数使用泰勒展开,然后应用多种组合性质来计算所需多项式的系数。文中讨论了该方法面临的主要计算挑战,以及通过在训练阶段施加某些约束来克服这些挑战的方法。最后,通过仿真实验以及对真实表格数据的应用,展示了所提方法的有效性。

英文摘要:

Interpretability of neural networks and their underlying theoretical behavior remain an open field of study even after the great success of their practical applications, particularly with the emergence of deep learning. In this work, NN2Poly is proposed: a theoretical approach to obtain an explicit polynomial model that provides an accurate representation of an already trained fully-connected feed-forward artificial neural network (a multilayer perceptron or MLP). This approach extends a previous idea proposed in the literature, which was limited to single hidden layer networks, to work with arbitrarily deep MLPs in both regression and classification tasks. NN2Poly uses a Taylor expansion on the activation function, at each layer, and then applies several combinatorial properties to calculate the coefficients of the desired polynomials. Discussion is presented on the main computational challenges of this method, and the way to overcome them by imposing certain constraints during the training phase. Finally, simulation experiments as well as applications to real tabular data sets are presented to demonstrate the effectiveness of the proposed method.

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。

↑