| Project/Area Number |
18K04266
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 21060:Electron device and electronic equipment-related
|
|---|
| Research Institution | Kyushu Institute of Technology |
|---|
Principal Investigator |
Nakamura Kazuyuki 九州工業大学, マイクロ化総合技術センター, 教授 (60336097)
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2018: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | ニューラルネットワーク / 連想メモリ / SRAM / 人工知能 / 推論 / LUTカスケード / TCAM / ニューラルネット / 脳型LSI / レシオレス |
|---|
| Outline of Final Research Achievements |
To demonstrate the basic idea of the proposed NN-TCAM (Neural Network-TCAM), I conducted functional design to confirm its architectural behavior. First, we developed an NN-TCAM simulator by C-program and successfully verified the basic scheme. Furthermore, we modified the ratio-less TCAM chip and proceeded with the circuit design of the basic core part.
In the research process, we investigated a new configuration based on multi-level accesses of memory, which is a major problem for power consumption, and came to propose the following research topic, "21K04179: Research on realization of memory-driven artificial intelligence LSI with memory cascade configuration.
|
| Academic Significance and Societal Importance of the Research Achievements |
TCAM上にニューラルネットワークをエントリとして直接マッピングし、駆動演算する本提案は、学術的に全く独創的で、従来のデジタル方式とアナログ方式の中間に位置付けられ、エッジにおいて使用環境への適応化のための学習機能にも対応可能であり、高い産業的価値を持つ。
長年我が国の半導体設計技術の中核であったメモリ技術の延長にあり、第３の新たな脳型ハードウエアの実現候補として、新たなメモリの応用分野を切り開くものである。
|
