The quest for a Quantum Neural Network

By Maria Schuld, Ilya Sinayskiy, Francesco Petruccione. Quantum Information Processing, 2014

694 citations recorded by the source corpus.

With the overwhelming success in the field of quantum information in the last decades, the ‘quest’ for a Quantum Neural Network (QNN) model began in order to combine quantum computing with the striking properties of neural computing. This article presents a systematic approach to QNN research, which so far consists of a conglomeration of ideas and proposals. Concentrating on Hopfield-type networks and the task of associative memory, it outlines the challenge of combining the nonlinear, dissipative dynamics of neural computing and the linear, unitary dynamics of quantum computing. It establishes requirements for a meaningful QNN and reviews existing literature against these requirements. It is found that none of the proposals for a potential QNN model fully exploits both the advantages of quantum physics and computing in neural networks. An outlook on possible ways forward is given, emphasizing the idea of Open Quantum Neural Networks based on dissipative quantum computing.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/7e93780bd9676cc370f80207f5fb1bd3acfb98b2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Quantum machine learning: a classical perspective (2017, methodology): “[142] provides a critical overview of the different strategies employed to build”
Noise-induced barren plateaus in variational quantum algorithms (2020, background): “Our results also generalize to settings that allow for multiple input states or training data, as in machine learning applications, often called quantum neural networks [58–62].”
Quantum-enhanced machine learning (2016, background): “QC corresponds to quantum QC corresponds to quantum variants of learning algorithms [7, 10, 21] facing a classical environment. variants of learning algorithms [7, 10, 19] facing a classical environment.”
Challenges and opportunities in quantum machine learning (2022, background): “Many other QNNs have been proposed [41–45], and constructing QNN architectures is currently an active area of research.”
Continuous-variable quantum neural networks (2018, background): “[61] Maria Schuld, Ilya Sinayskiy, and Francesco Petruc-”
Experimental photonic quantum memristor (2021, background): “However, quantum neural networks are technologically challenging as the underlying computation requires non-unitary operations for mimicking the behavior of neurons [9].”
Entanglement Induced Barren Plateaus (2020, background): “The QML ﬁeld has enjoyed increased attention for quantum algorithms for principal component analysis [1], support vector machines [2], kernel meth-ods [3, 4], and quantum neural networks (QNN) [3, 5–8] but experiences setbacks in the form of dequantization techniques [9–11].”
An introduction to quantum machine learning (2014, background): “However, it is an interesting open challenge to translate the nonlinear activation function into a meaningful quantum mechanical framework [7], or to ﬁnd learning schemes based on quantum superposition and parallelism.”
Absence of Barren Plateaus in Quantum Convolutional Neural Networks (2020, background): “Among the most promising applications are variational quantum algorithms (VQAs) [17–26], and more generally, quantum neural networks (QNNs) [27–34].”
Quantum machine learning (2016, neutral): “Yet at the same time, certain powerful and central ideas in the theory of machine learning—such as neural computing [119], quantum generalizations of Bayesian networks [56] and quantum causal models [99]—seem to necessitate an increased eﬀort to understand several fundamental questions attached to…”