The recent advances in real Quantum Computing have lent credibility and acclaim to the idea of using Parameterized Quantum Computing methods as hypotheses for Quantum-Classical Hybrid Machine Learning Systems. Quantum-Classical Hybrid systems are the next step towards comprehensive Quantum Enhanced Systems. They have already shown great promise and potential in solving supervised and generative learning tasks with recent works demonstrating their superiority in specialized Artificial Intelligence tasks as well. However, the largest impact that Quantum Advantage can bring about in present-day systems lies in optimizing the hardest and most complex parallel learning algorithms. From this perspective, this research compares three of the most challenging artificial intelligence algorithms that illustrate the leverage which can be obtained by harnessing the properties of quantum computing. In this paper, Quantum Enhanced Reinforcement Learning, Genetic Algorithms and Particle Swarm Optimization are explored with an emphasis on the applications of Particle Swarm Optimization.
Article Details
Unique Paper ID: 159381
Publication Volume & Issue: Volume 9, Issue 11
Page(s): 985 - 993
Article Preview & Download
Share This Article
Conference Alert
NCSST-2021
AICTE Sponsored National Conference on Smart Systems and Technologies
Last Date: 25th November 2021
SWEC- Management
LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT