Thermally Stable Ag2Se Nanowire Network as an Effective In-Materio Physical Reservoir Computing Device

被引：0

作者：

Kotooka, Takumi ^{[1
]}

Lilak, Sam ^{[2
]}

Stieg, Adam Z. ^{[3
,4
]}

Gimzewski, James K. ^{[2
,3
,4
,5
]}

Sugiyama, Naoyuki ^{[6
]}

Tanaka, Yuichiro ^{[1
,5
]}

Kawabata, Takuya ^{[1
]}

Karacali, Ahmet ^{[1
]}

Tamukoh, Hakaru ^{[1
,5
]}

Usami, Yuki ^{[1
,5
]}

Tanaka, Hirofumi ^{[1
,5
]}

机构：

[1] Kyushu Inst Technol Kyutech, Grad Sch Life Sci & Syst Engn, Dept Human Intelligence Syst, 2-4 Hibikino, Aizu Wakamatsu, Kitakyushu 8080196, Japan

[2] Univ Calif Los Angeles UCLA, Dept Chem & Biochem, Los Angeles, CA 90095 USA

[3] Univ Calif Los Angeles UCLA, Calif Nanosyst Inst, Los Angeles, CA 90095 USA

[4] Natl Inst Mat Sci NIMS, WPI Ctr Mat Nanoarchitecton MANA, Tsukuba 3050044, Japan

[5] Kyushu Inst Technol Kyutech, Res Ctr Neuromorph AI Hardware, Kitakyushu 8080196, Japan

[6] Toray Res Ctr Ltd, Morphol Res Lab, 3-2-11 Sonoyama, Otsu, Shiga 5200842, Japan

来源：

ADVANCED ELECTRONIC MATERIALS | 2024年 / 10卷 / 12期

关键词：

reservoir computing; silver selenide nanowire network; voice classification; SELENIUM NANOWIRES;

D O I：

10.1002/aelm.202400443

中图分类号：

TB3 [工程材料学];

学科分类号：

0805 ; 080502 ;

摘要：

The artificial intelligence (AI) paradigm shifts from software to implementing general-purpose or application-specific hardware systems with lower power requirements. This study explored a material physical reservoir consisting of a material random network, called in-materio physical reservoir computing (RC) to achieve efficient hardware systems. The device, made up of a random, highly interconnected network of nonlinear Ag2Se nanojunctions as reservoir nodes, demonstrated the requisite characteristics of an in-materio physical reservoir, including but not limited to nonlinear switching, memory, and higher harmonic generation. The power consumption of the in-materio physical reservoir is 0.07 nW per nanojunctions, confirming its highly efficient information processing system. As a hardware reservoir, the devices successfully performed waveform generation tasks. Finally, a voice classification by an in-materio physical reservoir is achieved over 80%, comparable to an RC software simulation. In-materio physical RC with rich nonlinear dynamics has huge potential for next-generation hardware-based AI.

引用

页数：10