arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.09399cs.LGmath-phmath.DSmath.MPquant-ph
收藏

连续时间循环神经网络的波函数

The Wavefunction of Continuous-Time Recurrent Neural Networks

York University(约克大学)

Ikjyot Singh Kohli, Michael C. Haslam

摘要:

本文探讨了连续时间递归神经网络(CTRNN)量子波函数的可能性。我们首先从一个描述连续时间递归神经网络经典动力学的二维动力学系统开始,然后推导出一个哈密顿量。在此之后,我们使用Weyl量化在Hilbert空间$\mathbb{H} = L^2(\mathbb{R})$上量化该哈密顿量。然后,我们解决了薛定谔方程,给我们的波函数在库默尔的合流超几何函数对应的神经网络结构。在无穷远处应用空间边界条件时,我们能够导出对神经网络的权重和超参数的条件/限制,这可能会对找到所述神经网络的最佳权重的性质提供见解。

英文摘要:

In this paper, we explore the possibility of deriving a quantum wavefunction for continuous-time recurrent neural network (CTRNN). We did this by first starting with a two-dimensional dynamical system that describes the classical dynamics of a continuous-time recurrent neural network, and then deriving a Hamiltonian. After this, we quantized this Hamiltonian on a Hilbert space $\mathbb{H} = L^2(\mathbb{R})$ using Weyl quantization. We then solved the Schrodinger equation which gave us the wavefunction in terms of Kummer's confluent hypergeometric function corresponding to the neural network structure. Upon applying spatial boundary conditions at infinity, we were able to derive conditions/restrictions on the weights and hyperparameters of the neural network, which could potentially give insights on the the nature of finding optimal weights of said neural networks.

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。

↑