Quantum Neural Machine Learning - Backpropagation and Dynamics

TL;DR

This paper introduces a quantum neural network framework that combines learning and backpropagation stages, enabling self-programming quantum systems with dynamic, noise-resilient behavior.

Contribution

It presents a novel quantum neural network model with integrated backpropagation and dynamic self-organization, extending to recurrent architectures interacting with environments.

Findings

Networks converge to specific quantum circuits.

Recurrent networks exhibit noise-resilient dynamics.

Self-organizing behavior emerges in quantum neural systems.

Abstract

The current work addresses quantum machine learning in the context of Quantum Artificial Neural Networks such that the networks' processing is divided in two stages: the learning stage, where the network converges to a specific quantum circuit, and the backpropagation stage where the network effectively works as a self-programing quantum computing system that selects the quantum circuits to solve computing problems. The results are extended to general architectures including recurrent networks that interact with an environment, coupling with it in the neural links' activation order, and self-organizing in a dynamical regime that intermixes patterns of dynamical stochasticity and persistent quasiperiodic dynamics, making emerge a form of noise resilient dynamical record.