Hybrid Quantum-Classical Approach: Quantum-Inspired Deep Learning Using Classical Simulation
Year: 2023
Type: preprint
Abstract: In this groundbreaking investigation, we delve into the fertile intersection of quantum mechanics and deep learning, introducing a unique hybrid quantum-classical approach that holds promising implications for the advancement of Artificial Intelligence (AI). Expanding upon the Deep Learning algorithm, we put forth Quantum Deep Learning (QDL), an innovative methodology that synergistically intertwines quantum principles with deep learning algorithms, facilitated by simulation on classical computational platforms. Through this intricate blend, we aim to harness the colossal computational prowess of quantum mechanics, setting the stage for unprecedented improvements in AI model performance. This research paves the way for a transformative future in AI, where quantum-inspired deep learning techniques could redefine the landscape of AI applications.
Source: Research Square
Author: Esmaeil Farshi
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4379792011