Thermally Stable Ag2Se Nanowire Network as an Effective In-Materio Physical Reservoir Computing Device,Advanced Electronic Materials

当前位置： X-MOL 学术 › Adv. Electron. Mater. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Thermally Stable Ag2Se Nanowire Network as an Effective In-Materio Physical Reservoir Computing Device
Advanced Electronic Materials ( IF 5.3 ) Pub Date : 2024-11-27 , DOI: 10.1002/aelm.202400443
Takumi Kotooka ₁ , Sam Lilak ₂ , Adam Z. Stieg _{3,

4} , James K. Gimzewski _{2,

3,

4,

5} , Naoyuki Sugiyama ₆ , Yuichiro Tanaka _{1,

5} , Takuya Kawabata ₁ , Ahmet Karacali ₁ , Hakaru Tamukoh _{1,

5} , Yuki Usami _{1,

5} , Hirofumi Tanaka _{1,

5}

Affiliation

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.

中文翻译：

热稳定 Ag2Se 纳米线网络作为有效的材料内物理储层计算设备

人工智能（AI）范式从软件转变为实现具有较低功耗要求的通用或特定于应用的硬件系统。本研究探索了一种由材料随机网络组成的材料物理储层，称为材料内物理储层计算（RC），以实现高效的硬件系统。该装置由非线性 Ag₂Se 纳米结的随机、高度互连网络组成，作为储层节点，展示了天然物理储层的必要特性，包括但不限于非线性开关、内存和高次谐波产生。内部物理储层的功耗为每纳米结 0.07 nW，证实了其高效的信息处理系统。作为硬件存储库，这些设备成功地执行了波形生成任务。最后，通过材料物理储层实现的语音分类超过 80%，可与 RC 软件仿真相媲美。具有丰富非线性动力学的 In-materio 物理 RC 在下一代基于硬件的 AI 中具有巨大潜力。

更新日期：2024-11-27

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南