arXiv:1808.09058 · International Journal of Quantum Information

Quantum enhanced cross-validation for near-optimal neural networks architecture selection

Priscila G. M. dos Santos, Rodrigo S. Sousa, Ismael C. S. Araujo, Adenilton J. da Silva

Published Sep 13, 2018• 7 citations

Abstract

This paper proposes a quantum-classical algorithm to evaluate and select classical artificial neural networks architectures. The proposed algorithm is based on a probabilistic quantum memory (PQM) and the possibility to train artificial neural networks (ANN) in superposition. We obtain an exponential quantum speedup in the evaluation of neural networks. We also verify experimentally through a reduced experimental analysis that the proposed algorithm can be used to select near-optimal neural networks.

DOI: 10.1142/s0219749918400051

Related papers

Artificial neural network architecture selection in a quantum computer

Adenilton José da Silva

Miniaturisation of computers components is taking us from classical to quantum physics domain. Further reduction in computer components size eventually will lead to the development of computer systems whose components will be on such a small scale that quantum physics intrinsic properties must be taken into account. The expression quantum computation and a first formal model of a quantum computer were first employed in the eighties. With the discovery of a quantum algorithm for factoring exponentially faster than any known classical algorithm in 1997, quantum computing began to attract industry investments for the development of a quantum computer and the design of novel quantum algorithms. For instance, the development of learning algorithms for neural networks. Some artificial neural networks models can simulate an universal Turing machine, and together with learning capabilities have numerous applications in real life problems. One limitation of artificial neural networks is the lack of an efficient algorithm to determine its optimal architecture. The main objective of this work is to verify whether we can obtain some advantage with the use of quantum computation techniques in a neural network learning and architecture selection procedure. We propose a quantum neural network, named quantum perceptron over a field (QPF). QPF is a direct generalisation of a classical perceptron which addresses some drawbacks found in previous models for quantum perceptrons. We also present a learning algorithm named Superposition based Architecture Learning algorithm (SAL) that optimises the neural network weights and architectures. SAL searches for the best architecture in a finite set of neural network architectures and neural networks parameters in linear time over the number of examples in the training set. SAL is the first quantum learning algorithm to determine neural network architectures in linear time. This speedup is obtained by the use of quantum parallelism and a non linear quantum operator.

Jun 26, 20150 citations

Quantum Enhanced k-fold Cross-Validation

Priscila G. M. dos Santos, Ismael C. S. Araújo, Rodrigo S. Sousa +1 more

In this work, we propose a quantum-classical algorithm able to perform a k-fold cross-validation with linear speedup. The proposed method creates a quantum superposition with patterns from a dataset and a classifier can evaluate all patterns at once. We used a probabilistic quantum memory in order to conduct the performance evaluation. The proposed method was verified through a reduced experimental analysis conducted classically.

Brazilian Conference on Intelligent SystemsOct 1, 20183 citations

Neural Networks Architecture Evaluation in a Quantum Computer

Adenilton Jose da Silva, Rodolfo Luan Franco de Oliveira

In this work, we propose a quantum algorithm to evaluate neural networks architectures named Quantum Neural Network Architecture Evaluation (QNNAE). The proposed algorithm is based on a quantum associative memory and the learning algorithm for artificial neural networks. Unlike conventional algorithms for evaluating neural network architectures, QNNAE does not depend on initialization of weights. The proposed algorithm has a binary output and results in 0 with probability proportional to the performance of the network. And its computational cost is equal to the computational cost to train a neural network.

arXiv:1711.04759Brazilian Conference on Intelligent SystemsOct 1, 20177 citations

Optimized Quantum-Enhanced Neural Network Architectures

T. Ranjitha Devi, Yogendra Chhetri, Regonda Nagaraju +3 more

Recent developments in quantum machine learning, there is focus on how the abilities of quantum-based neural architectures, which current purely classical systems cannot achieve, can be utilized to model more complex data connections. To circumvent this issue, this paper suggests an efficient quantum-enhanced neural network model that jointly optimizes model structure, learning dynamics, and hybridization in the process of training. This architecture provides a hybrid of classical feature processing and variational quantum circuits where the performance-based architectural control enables the introduction of quantum elements selectively, as opposed to uniformly. This twin-engine design stresses on stability, awareness of resources and cross-framework deplorability. The classical, hybrid, and quantum-enhanced versions of the device can be evaluated experimentally, showing a consistent improvement of performance.

Advances in computational intelligence and robotics book seriesApr 1, 20260 citations

Quantum Walk-Based Optimization of Neural Network Architectures

Jincheng Zhang

This paper investigates the application of quantum walks to the optimization of neural network architectures, a problem traditionally addressed through computationally intensive classical methods. The core idea is to leverage the inherent parallelism and probabilistic nature of quantum walks to efficiently explore the vast architecture space of neural networks. We propose a framework where a quantum walk is performed on a graph representing candidate neural network architectures. The walk's evolution is governed by a Hamiltonian operator designed to encourage the selection of architectures with desirable performance characteristics, as measured by a predefined objective function. Through theoretical analysis and conceptual design, we demonstrate the potential for quantum walks to achieve significant speedups compared to traditional NAS algorithms, potentially realizing exponential improvements in the search process. The exploration of this approach opens new avenues for designing high-performing neural networks with reduced computational costs.

Sep 2, 20260 citations

Quantum-Assisted Optimization of Neural Network Architecture

Jincheng Zhang

Quantum-assisted optimization of neural network architecture is a burgeoning field aiming to accelerate the design and training of deep learning models. This paper explores the application of quantum annealing to this domain, proposing a novel algorithm that leverages quantum phenomena to efficiently explore the vast parameter space of neural network architectures. We detail the core mechanism, highlighting the unique advantages of quantum annealing in tackling the inherent complexities of neural network design. The paper presents a comprehensive analysis of the theoretical underpinnings, experimental validation, and potential future directions of this research. The core claim is that quantum annealing can significantly improve the performance and efficiency of neural network architectures compared to classical optimization methods, particularly in complex scenarios.

Sep 3, 20260 citations