arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.02676cs.NEcs.AIcs.LG
收藏

节能添加剂神经网络

Energy Saving Additive Neural Network

Middle East Technical University(中东技术大学);Bilkent University(比尔肯大学)

Arman Afrasiyabi, Ozan Yildiz, Baris Nasir, Fatos T. Yarman Vural, A. Enis Cetin

摘要:

近年来,基于神经网络的机器学习技术在移动计算中的应用越来越广泛。经典的多层神经网络在每一阶段都需要矩阵乘法。乘法操作不是能量有效的操作,因此它耗尽了移动终端的电池。本文提出了一种新的能量有效的神经网络,它具有Lebesgue可积函数空间上的普适逼近性质。这种网络称为加性神经网络,非常适合于移动计算。神经结构是基于一种新的向量积定义,称为EF-运算符,允许无乘法器的实现。在ef运算中,两个实数的乘积定义为它们的绝对值之和,其符号由这两个数的乘积的符号决定。该“产物”用于在$R^N$中构建载体产物。向量积导出$l_1$范数。所提出的加性神经网络成功地解决了异或问题。在MNIST数据集上的实验表明,所提出的加性神经网络的分类性能与相应的多层感知器和卷积神经网络(LeNet)非常相似.

英文摘要:

In recent years, machine learning techniques based on neural networks for mobile computing become increasingly popular. Classical multi-layer neural networks require matrix multiplications at each stage. Multiplication operation is not an energy efficient operation and consequently it drains the battery of the mobile device. In this paper, we propose a new energy efficient neural network with the universal approximation property over space of Lebesgue integrable functions. This network, called, additive neural network, is very suitable for mobile computing. The neural structure is based on a novel vector product definition, called ef-operator, that permits a multiplier-free implementation. In ef-operation, the "product" of two real numbers is defined as the sum of their absolute values, with the sign determined by the sign of the product of the numbers. This "product" is used to construct a vector product in $R^N$. The vector product induces the $l_1$ norm. The proposed additive neural network successfully solves the XOR problem. The experiments on MNIST dataset show that the classification performances of the proposed additive neural networks are very similar to the corresponding multi-layer perceptron and convolutional neural networks (LeNet).

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。

↑