Ziyuan Meng, Hang Xu, Xueli Geng, Zhaoying Ren, Haifeng Feng, Kunrong Du, Zhijian Shi, Wei Cai, Zhe Sun, Hongrun Zhang, Anping Huang, Feng Cheng, Binghui Ge, Yi Du, Weichang Hao
{"title":"Analog ReLU Activation Enabled by Van Hove Singularities in a Kagome Semiconductor Field‐Effect Transistor","authors":"Ziyuan Meng, Hang Xu, Xueli Geng, Zhaoying Ren, Haifeng Feng, Kunrong Du, Zhijian Shi, Wei Cai, Zhe Sun, Hongrun Zhang, Anping Huang, Feng Cheng, Binghui Ge, Yi Du, Weichang Hao","doi":"10.1002/aelm.202500255","DOIUrl":null,"url":null,"abstract":"With the growing demand for high‐performance computing in deep learning, energy‐efficient analog computing has emerged as a promising alternative to conventional energy‐intensive digital processing. A major obstacle in this field is the physical realization of activation functions, due to the lack of analog f (FETs) that inherently exhibit the desired piecewise‐linear transfer characteristics. Here, a novel strategy is presented for implementing the Rectified Linear Unit (ReLU) activation function by exploiting the high density of states (DOS) associated with van Hove singularities (vHs), induced by flat bands in a kagome semiconductor Nb<jats:sub>3</jats:sub>Cl<jats:sub>8</jats:sub> FET. This vHs‐enhanced DOS imparts pronounced piecewise‐linear transfer behavior at low temperatures, effectively mimicking the ReLU function. To enable room‐temperature operation, the origin of the hysteresis commonly observed in Nb<jats:sub>3</jats:sub>Cl<jats:sub>8</jats:sub> FETs is identified and addressed. Temperature‐dependent and time‐resolved measurements attribute the hysteresis to charge trapping at the Nb<jats:sub>3</jats:sub>Cl<jats:sub>8</jats:sub>–substrate interface. By introducing a hexagonal boron nitride (h‐BN) buffer layer, the hysteresis is successfully suppressed, achieving stable and highly linear transfer characteristics at room temperature. These results demonstrate the potential of vHs‐engineered electronic states for the physical implementation of analog activation functions, offering a pathway toward compact, high‐density, and energy‐efficient hardware for analog deep learning accelerators.","PeriodicalId":110,"journal":{"name":"Advanced Electronic Materials","volume":"27 1","pages":""},"PeriodicalIF":5.3000,"publicationDate":"2025-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advanced Electronic Materials","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1002/aelm.202500255","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
With the growing demand for high‐performance computing in deep learning, energy‐efficient analog computing has emerged as a promising alternative to conventional energy‐intensive digital processing. A major obstacle in this field is the physical realization of activation functions, due to the lack of analog f (FETs) that inherently exhibit the desired piecewise‐linear transfer characteristics. Here, a novel strategy is presented for implementing the Rectified Linear Unit (ReLU) activation function by exploiting the high density of states (DOS) associated with van Hove singularities (vHs), induced by flat bands in a kagome semiconductor Nb3Cl8 FET. This vHs‐enhanced DOS imparts pronounced piecewise‐linear transfer behavior at low temperatures, effectively mimicking the ReLU function. To enable room‐temperature operation, the origin of the hysteresis commonly observed in Nb3Cl8 FETs is identified and addressed. Temperature‐dependent and time‐resolved measurements attribute the hysteresis to charge trapping at the Nb3Cl8–substrate interface. By introducing a hexagonal boron nitride (h‐BN) buffer layer, the hysteresis is successfully suppressed, achieving stable and highly linear transfer characteristics at room temperature. These results demonstrate the potential of vHs‐engineered electronic states for the physical implementation of analog activation functions, offering a pathway toward compact, high‐density, and energy‐efficient hardware for analog deep learning accelerators.
期刊介绍:
Advanced Electronic Materials is an interdisciplinary forum for peer-reviewed, high-quality, high-impact research in the fields of materials science, physics, and engineering of electronic and magnetic materials. It includes research on physics and physical properties of electronic and magnetic materials, spintronics, electronics, device physics and engineering, micro- and nano-electromechanical systems, and organic electronics, in addition to fundamental research.