Authors: Siraj Raval
Deep learning has resulted in state of the art performance for automated tasks in the fields of natural language processing, computer vision, autonomous driving, and many other subfields of Artificial Intelligence. However, if the goal is to create a system that is capable of learning any task, given an objective function, I hypothesize that it’s necessary to reconsider classical neural network architecture to incorporate certain properties of quantum mechanics, namely superposition and entanglement. Building on the work of Fisher , I surmise that Phosphorus-31 enables both of these properties to occur within neurons in the human brain. In light of this evidence, quantum information processing in the context of digital neural networks is an area that deserves further exploration. As such, I present a novel quantum neural network architecture, similar to the continuous variable archicecture by Killoran et al. . It was applied to a transaction dataset for a fraud detection task and attained a considerable accuracy score. My aim is that this will provide a starting point for more research in this space, ultimately using this technology to drive more innovation in every Scientific discipline, from Pharmacology to Computer Science.
Comments: 10 Pages.
[v1] 2019-09-03 21:38:09
Unique-IP document downloads: 68 times
Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.
Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.