arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.07033cs.LGstat.ML
收藏

向量场神经网络

Vector Field Neural Networks

Universidade Federal do Rio de Janeiro(里约热内卢联邦大学);Instituto Tércio Pacitti de Aplicações e Pesquisas Computacionais(特尔西奥·帕奇蒂计算机应用与研究所)

Daniel Vieira, Joao Paixao

摘要:

这项工作开始于建立一个数学形式化之间的不同几何解释的神经网络,提供了第一个贡献。从这个出发点,探索一种新的解释,使用隐式矢量场的想法移动数据作为粒子流。在此基础上提出了一种新的结构--向量场神经网络(VFNN),使向量场变得显式。一个具体的实施VFNN使用欧拉的方法来解决常微分方程(ODE)和高斯向量场进行测试。第一个实验呈现视觉结果,重新标记的新架构的重要功能,并提供另一个贡献与几何解释的正则化模型参数。然后,针对不同的超参数和输入对新架构进行评估,目的是评估对模型性能、计算时间和复杂度的影响。VFNN模型与已知的基本模型朴素贝叶斯,前馈神经网络,和支持向量机(SVM)进行比较,显示出可比的,或更好的,不同的数据集的结果。最后,本文的结论为模型的改进提出了新的问题和思路,可用于提高模型的性能。

英文摘要:

This work begins by establishing a mathematical formalization between different geometrical interpretations of Neural Networks, providing a first contribution. From this starting point, a new interpretation is explored, using the idea of implicit vector fields moving data as particles in a flow. A new architecture, Vector Fields Neural Networks(VFNN), is proposed based on this interpretation, with the vector field becoming explicit. A specific implementation of the VFNN using Euler's method to solve ordinary differential equations (ODEs) and gaussian vector fields is tested. The first experiments present visual results remarking the important features of the new architecture and providing another contribution with the geometrically interpretable regularization of model parameters. Then, the new architecture is evaluated for different hyperparameters and inputs, with the objective of evaluating the influence on model performance, computational time, and complexity. The VFNN model is compared against the known basic models Naive Bayes, Feed Forward Neural Networks, and Support Vector Machines(SVM), showing comparable, or better, results for different datasets. Finally, the conclusion provides many new questions and ideas for improvement of the model that can be used to increase model performance.

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。

↑