6360069
doi
10.48550/arXiv.2103.11307
oai:zenodo.org:6360069
Betis Baheri
Kent State University
Daniel Chen
Case Western Reserve University
Ying Mao
Fordham University
Qiang Guan
Kent State University
Shuai Xu
Case Western Reserve University
Caiwen Ding
University of Conneticut
Ang Li
Pacific Northwest National Laboratory
QuClassi: A Hybrid Deep Neural Network Architecture based on Quantum State Fidelity
Samuel A. Stein
Pacific Northwest National Laboratory
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
<p>QuClassi: A Hybrid Deep Neural Network Architecture based on Quantum State Fidelity</p>
<p>MLSys 2022 Publication</p>
<p>QuClassi is a Quantum Deep Neural Network architecture for classification, based on quantum state fidelity</p>
<p>Usage</p>
<p>To use QuClassi, install the requirements by using</p>
<pre>pip install -r requirements.txt</pre>
<p>Within main.py, there is a subsampling section</p>
<pre>SUBSAMPLE = 1000</pre>
<p>This is to be edited according to computational constraints. More data results in slower training speeds, and hence subsamples are used for quicker evaluation.</p>
<p>From here, to run the system, run the command</p>
<pre>python main.py</pre>
<p>Subsample sets can be edited by editting the training labels and training datasets accordingly.</p>
Zenodo
2021-03-21
info:eu-repo/semantics/conferencePaper
6360068
1647395383.145889
13162
md5:eebde725c0574f283c77565a43ae2266
https://zenodo.org/records/6360069/files/main.py
57
md5:59b869ff15852bb1d3a3d0c78534ab2f
https://zenodo.org/records/6360069/files/requirements.txt
823
md5:0e43899cb15b00c8a297bc079395789c
https://zenodo.org/records/6360069/files/README.md
public