This paper explores a novel approach to quantum algorithm optimization by leveraging the inherent capabilities of multi-scale self-organizing neural networks (MSSONNs). The core idea is to transform the optimization of quantum algorithms into a training problem for MSSONNs, allowing the network to autonomously discover optimal structures and parameters. We propose a framework where the quantum algorithm's objective function is mapped onto the MSSONN's loss function. Through iterative training, the MSSONN adapts and evolves, effectively automating the design and refinement of quantum algorithms. This work demonstrates the potential for significantly reducing the manual effort involved in quantum algorithm development, accelerating the discovery of efficient solutions, and ultimately unlocking the full potential of quantum computation. The key contribution lies in the synergistic combination of neural network self-organization and quantum algorithm optimization, leading to an adaptive and automated process. ---
This paper highlights a practical research of the possibility of forming quantum circuits for training neural networks. The demonstrated quantum circuits were based on the principles of Grover's Search Algorithm. The perceptron was chosen as the architecture for the example neural network. The multilayer perceptron is a popular neural network architecture due to its scalability and applicability for solving a wide range of problems. Large scale neural networks can require significant computing resources for training purposes, therefore Grover’s quantum search algorithm could be used as a way to speed up this process, thanks to its ability of simultaneously processing multiple input values of a given function.
Unsupervised machine learning is one of the main techniques employed in artificial intelligence. We introduce an algorithm for quantum-assisted unsupervised data clustering using the self-organizing feature map, a type of artificial neural network. The complexity of our algorithm scales as
O(LN), in comparison to the classical case which scales as
O(LMN), where
N is the number of samples,
M is the number of randomly sampled cluster vectors, and
L is the number of the shifts of cluster vectors. We perform a proof-of-concept demonstration of one of the central components on the IBM quantum computer and show that it allows us to reduce the number of calculations in the number of clusters. Our algorithm exhibits exponential decrease in the errors of the distance matrix with the number of runs of the algorithm.