Quantum and Quantum-inspired Machine Learning: from foundations to theoretical advances

This topical collection aims to explore both the foundational theories of Quantum Machine Learning (QML) and its theoretical advancements. This collection will delve into the intrinsic and foundational quantum properties that lend themselves to machine learning and how these characteristics can be harnessed to improve learning models. The topics of focus will include, but are not limited to, theoretical and foundational aspects of quantum machine learning, quantum-inspired machine learning and quantum-inspired optimization techniques. In particular, Quantum-inspired Machine Learning (QiML) is recognized as a fascinating field, which uses the mathematical formalisms of quantum theory without the necessity of a physical quantum system. This collection also invites discussions and research on the theoretical developments in QiML, exploring how principles of quantum mechanics can be used to develop machine learning methods that outperform traditional approaches and what could be the possible implications from a foundational viewpoint. Papers are sought from researchers and scholars that contribute to the fundamental understanding of quantum and quantum-inspired phenomena in machine learning, that present theoretical developments, or propose innovative methodologies that exploit these phenomena. The objective of this collection is to offer a comprehensive resource for researchers interested in the latest advancements in quantum and quantum-inspired machine learning, providing valuable insights into the ongoing foundational and theoretical developments in these rapidly evolving fields. Submissions can range from purely foundational papers to those which include theoretical analysis. The collection will foster the exchange of ideas, facilitating collaboration and inspiring further research in these domains. Topics covered are: ● Foundational Theories of Quantum Machine Learning: Delving into the intrinsic quantum mechanical foundations integral to QML. ● Quantum and Quantum-inspired Machine Learning: Theoretical frameworks for implementing quantum formalisms in machine learning without quantum devices. Understanding how quantum phenomena can enhance machine learning. ● Theoretical implications of QML and QiML: Investigating potential consequences and novel theoretical insights in quantum and quantum-inspired machine learning.