This website requires JavaScript.

A Quantum Information Theoretic View On A Deep Quantum Neural Network

Beatrix C. Hiesmayr
Dec 2022
摘要
We discuss a quantum version of an artificial deep neural network where therole of neurons is taken over by qubits and the role of weights is played byunitaries. The role of the non-linear activation function is taken over bysubsequently tracing out layers (qubits) of the network. We study two examplesand discuss the learning from a quantum information theoretic point of view. Indetail, we show that the lower bound of the Heisenberg uncertainty relations isdefining the change of the gradient descent in the learning process. We raisethe question if the limit by Nature to two non-commuting observables,quantified in the Heisenberg uncertainty relations, is ruling the optimizationof the quantum deep neural network. We find a negative answer.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答