Sparse Random Signals for Fast Convergence on Invertible Logic
This paper introduces sparse random signals for fast convergence on invertible logic. Invertible logic based on a network of probabilistic nodes (spins), similar to a Boltzmann machine, can compute functions bidirectionally by reducing the network energy to the global minimum with the addition of ra...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9399449/ |
| _version_ | 1811210279377174528 |
|---|---|
| author | Naoya Onizawa Makoto Kato Hitoshi Yamagata Koji Yano Seiichi Shin Hiroyuki Fujita Takahiro Hanyu |
| author_facet | Naoya Onizawa Makoto Kato Hitoshi Yamagata Koji Yano Seiichi Shin Hiroyuki Fujita Takahiro Hanyu |
| author_sort | Naoya Onizawa |
| collection | DOAJ |
| description | This paper introduces sparse random signals for fast convergence on invertible logic. Invertible logic based on a network of probabilistic nodes (spins), similar to a Boltzmann machine, can compute functions bidirectionally by reducing the network energy to the global minimum with the addition of random signals. Here, we propose using sparse random signals that are generated by replacing a part of the typical <italic>dense</italic> random signals with zero values in probability. The sparsity of the random signals can induce a relatively relaxed transition of the spin network, reaching the global minimum energy at high probabilities. As a typical design example of invertible logic, invertible adders and multipliers are designed and evaluated. The simulation results show that the convergence speed with the proposed sparse random signals is roughly an order of magnitude faster than that with the conventional dense random signals. In addition, several key parameters are found and could be a guideline for fast convergence on general invertible logic. |
| first_indexed | 2024-04-12T04:53:06Z |
| format | Article |
| id | doaj.art-05da44989ad04d258f25535f090b2456 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T04:53:06Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-05da44989ad04d258f25535f090b24562022-12-22T03:47:14ZengIEEEIEEE Access2169-35362021-01-019628906289810.1109/ACCESS.2021.30720489399449Sparse Random Signals for Fast Convergence on Invertible LogicNaoya Onizawa0https://orcid.org/0000-0002-4855-7081Makoto Kato1Hitoshi Yamagata2Koji Yano3Seiichi Shin4Hiroyuki Fujita5Takahiro Hanyu6Research Institute of Electrical Communication, Tohoku University, Sendai, JapanResearch Institute of Electrical Communication, Tohoku University, Sendai, JapanAdvanced Research Laboratory, Canon Medical Systems Corporation, Otawara, JapanAdvanced Research Laboratory, Canon Medical Systems Corporation, Otawara, JapanAdvanced Research Laboratory, Canon Medical Systems Corporation, Otawara, JapanAdvanced Research Laboratory, Canon Medical Systems Corporation, Otawara, JapanResearch Institute of Electrical Communication, Tohoku University, Sendai, JapanThis paper introduces sparse random signals for fast convergence on invertible logic. Invertible logic based on a network of probabilistic nodes (spins), similar to a Boltzmann machine, can compute functions bidirectionally by reducing the network energy to the global minimum with the addition of random signals. Here, we propose using sparse random signals that are generated by replacing a part of the typical <italic>dense</italic> random signals with zero values in probability. The sparsity of the random signals can induce a relatively relaxed transition of the spin network, reaching the global minimum energy at high probabilities. As a typical design example of invertible logic, invertible adders and multipliers are designed and evaluated. The simulation results show that the convergence speed with the proposed sparse random signals is roughly an order of magnitude faster than that with the conventional dense random signals. In addition, several key parameters are found and could be a guideline for fast convergence on general invertible logic.https://ieeexplore.ieee.org/document/9399449/Stochastic computingBoltzmann machinebidirectional operations |
| spellingShingle | Naoya Onizawa Makoto Kato Hitoshi Yamagata Koji Yano Seiichi Shin Hiroyuki Fujita Takahiro Hanyu Sparse Random Signals for Fast Convergence on Invertible Logic IEEE Access Stochastic computing Boltzmann machine bidirectional operations |
| title | Sparse Random Signals for Fast Convergence on Invertible Logic |
| title_full | Sparse Random Signals for Fast Convergence on Invertible Logic |
| title_fullStr | Sparse Random Signals for Fast Convergence on Invertible Logic |
| title_full_unstemmed | Sparse Random Signals for Fast Convergence on Invertible Logic |
| title_short | Sparse Random Signals for Fast Convergence on Invertible Logic |
| title_sort | sparse random signals for fast convergence on invertible logic |
| topic | Stochastic computing Boltzmann machine bidirectional operations |
| url | https://ieeexplore.ieee.org/document/9399449/ |
| work_keys_str_mv | AT naoyaonizawa sparserandomsignalsforfastconvergenceoninvertiblelogic AT makotokato sparserandomsignalsforfastconvergenceoninvertiblelogic AT hitoshiyamagata sparserandomsignalsforfastconvergenceoninvertiblelogic AT kojiyano sparserandomsignalsforfastconvergenceoninvertiblelogic AT seiichishin sparserandomsignalsforfastconvergenceoninvertiblelogic AT hiroyukifujita sparserandomsignalsforfastconvergenceoninvertiblelogic AT takahirohanyu sparserandomsignalsforfastconvergenceoninvertiblelogic |