Comments on “quantum artificial neural networks with applications”

详细信息    查看全文

• 作者：Adenilton J. da Silva ; ^{adenilton.silva@ufrpe.br" class="auth_mail" title="E-mail the corresponding author} ; ^{adenilton.silva@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Wilson R. de Oliveira
• 关键词：Quantum neural networks ; Quantum-inspired neural networks ; Universal approximation theorem
• 刊名：Information Sciences
• 出版年：2016
• 出版时间：20 November 2016
• 年：2016
• 卷：370-371
• 期：Complete
• 页码：120-122
• 全文大小：230 K

文摘

In a recent paper, H. Cao et al. (Information Science 290 (2015) 1-6) proposed a neural network model called the quantum artificial neural network, which we dub the CCWNN. The main properties of the CCWNN are its capacity to receive quantum inputs, the possibility of implementing it in a quantum computer and its universal approximation theorem. In this comment, we show that the CCWNN is in fact equivalent to a classical neural network and that its universal approximation theorem can be derived from previous results in the literature.