arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.14115cs.LGcs.AI
收藏

负反馈系统作为机器学习系统的优化器

Negative Feedback System as Optimizer for Machine Learning Systems

University of North Carolina at Charlotte(北卡罗来纳大学夏洛特分校)

Md Munir Hasan, Jeremy Holleman

AI总结:

本文提出将负反馈系统的函数求逆过程作为机器学习优化的物理类比,证明其能学习不可微函数并在特定约束下等价于梯度下降,为神经网络优化提供了新视角。

摘要:

在高前向增益下,负反馈系统具有执行反馈路径中线性或非线性函数的逆函数的能力。负反馈系统的这一特性已被广泛应用于模拟电子电路中,以构建精确的闭环函数。本文描述了负反馈系统的函数求逆过程如何作为机器学习中优化技术的物理类比。我们表明,在基于梯度下降的方法失效的情况下,该过程能够学习一些不可微函数。我们还表明,在平方误差最小化的约束下,该优化过程可归约为梯度下降。我们独立于梯度下降方法,从负反馈系统的特性推导出了反向传播技术及深度网络的其他已知优化技术。这一分析为神经网络优化提供了一种新视角,并可能为开放问题提供新见解。

英文摘要:

With high forward gain, a negative feedback system has the ability to perform the inverse of a linear or non-linear function that is in the feedback path. This property of negative feedback systems has been widely used in analog electronic circuits to construct precise closed-loop functions. This paper describes how the function-inverting process of a negative feedback system serves as a physical analogy of the optimization technique in machine learning. We show that this process is able to learn some non-differentiable functions in cases where a gradient descent-based method fails. We also show that the optimization process reduces to gradient descent under the constraint of squared error minimization. We derive the backpropagation technique and other known optimization techniques of deep networks from the properties of negative feedback system independently of the gradient descent method. This analysis provides a novel view of neural network optimization and may provide new insights on open problems.

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。

↑