2023 Fiscal Year Research-status Report
Development of Fast and Highly Effective Feature Subset Selection Algorithms based on Novel Integration of Quantum Computing and Machine Learning
| Project/Area Number |
20K11939
|
|---|
| Research Institution | Iwate Prefectural University |
|---|
Principal Investigator |
チャクラボルティ バサビ 岩手県立大学, その他部局等, 特命教授 (90305293)
|
|---|
| Project Period (FY) |
2020-04-01 – 2025-03-31
|
| Keywords | Feature subset selection / Quantum based algorithm / Quantum optimization / Quantum machine learning |
|---|
| Outline of Annual Research Achievements |
Last year we summarized our research results and drafted a review paper on quantum computing and quantum based metaheuristic algorithms for feature subset selection. This year we examined the draft and revisited our research results from the beginning of the project. We found that our results need to be verified by using real quantum computers instead of only simulation experiments. For this purpose we communicated to research facilities in foreign countries. In May 2023, I visited Regensberg University of Applied Science and the laboratory of Prof. Wolfgang Mauerer, Faculty of Computer Science and Mathematics, OTH-Regensberg.
He works in the area of Quantum Computing and we exchanged ideas of how could we use quantum computing in solving feature selection problem and frame a general approach for quantum machine learning. I used the quantum computing facility of the university to run our proposed algorithms in a small scale environment. Ashis Kumar Mandal, one of the research collaborators of this project is visiting University of Saskatchewan from September 2023. He is engaged in using the university's quantum computing facility. We could run small scale programs in check the plausibility and efficiency of our proposed quantum based algorithms for optimal feature subset selection. We are currently compiling our new results to enhance the draft review paper and will submit to a journal.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
Our project progressed smoothly as we planned in the year 2023. We could complete our planned experiments.
|
| Strategy for Future Research Activity |
This year we are planning to execute more simulations using quantum computer for data sets containing moderately large number of features. We will compile the results in a paper and submit this paper and the review paper to journal.
I am also planning to attend International conference to communicate our new results.
|
