arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.08235cs.LGcs.AIstat.ML
收藏

基于向量场的神经网络

Vector Field Based Neural Networks

Universidade Federal do Rio de Janeiro (UFRJ)(里约热内卢联邦大学)

Daniel Vieira, Fabio Rangel, Fabricio Firmino, Joao Paixao

摘要:

提出了一种新的神经网络结构,它利用向量场作为隐含层的数学和物理上丰富的思想来执行数据中的非线性变换。数据点被解释为沿着由向量场定义的流移动的粒子,该向量场直观地表示期望的移动以实现分类。该架构将数据点从其原始配置移动到遵循向量场的流线的新配置,目的是实现类可分离的最终配置。通过梯度下降来学习该向量场,从而解决优化问题。

英文摘要:

A novel Neural Network architecture is proposed using the mathematically and physically rich idea of vector fields as hidden layers to perform nonlinear transformations in the data. The data points are interpreted as particles moving along a flow defined by the vector field which intuitively represents the desired movement to enable classification. The architecture moves the data points from their original configuration to anew one following the streamlines of the vector field with the objective of achieving a final configuration where classes are separable. An optimization problem is solved through gradient descent to learn this vector field.

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。

↑