Quantum activation functions for quantum neural networks
نویسندگان
چکیده
Abstract The field of artificial neural networks is expected to strongly benefit from recent developments quantum computers. In particular, machine learning, a class algorithms which exploit qubits for creating trainable networks, will provide more power solve problems such as pattern recognition, clustering and learning in general. building block feed-forward consists one layer neurons connected an output neuron that activated according arbitrary activation function. corresponding algorithm goes under the name Rosenblatt perceptron. Quantum perceptrons with specific functions are known, but general method realize on computer still lacking. Here, we fill this gap capable approximate any analytic given order its series. Unlike previous proposals providing irreversible measurement–based simplified functions, here show how function required accuracy without need measure states encoding information. Thanks generality construction, network may acquire universal approximation properties Hornik’s theorem. Our results recast science architecture gate-model
منابع مشابه
Quantum-inspired Neural Networks
Quantum computing (physically-based computation founded on quantum-theoretic concepts) is gaining prominence because of recent claims for its massively increased computational eeciency, its potential for bridging brain and mind, and its increasing relevance as computer technology develops into nanotechnology. Its impact on neural information processing has so far been minimal. This paper introd...
متن کاملQuantum neural networks
This chapter outlines the research, development and perspectives of quantum neural networks – a burgeoning new field which integrates classical neurocomputing with quantum computation [1]. It is argued that the study of quantum neural networks may give us both new undestanding of brain function as well as unprecedented possibilities in creating new systems for information processing, including ...
متن کاملOPTIMUM SHAPE DESIGN OF DOUBLE-LAYER GRIDS BY QUANTUM BEHAVED PARTICLE SWARM OPTIMIZATION AND NEURAL NETWORKS
In this paper, a methodology is presented for optimum shape design of double-layer grids subject to gravity and earthquake loadings. The design variables are the number of divisions in two directions, the height between two layers and the cross-sectional areas of the structural elements. The objective function is the weight of the structure and the design constraints are some limitations on str...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Quantum Information Processing
سال: 2022
ISSN: ['1573-1332', '1570-0755']
DOI: https://doi.org/10.1007/s11128-022-03466-0