Scholarlink

<p>With the rise of data-centric applications such as edge AI and neuromorphic computing, there is increasing demand for memory solutions that overcome the limitations of conventional nonvolatile devices. Selector-only memory (SOM), which stores data through threshold voltage (V<sub>th</sub>) modulation in chalcogenide-based selector materials, offers a compact and scalable alternative. However, narrow read window margins and V<sub>th</sub> drift remain major reliability concerns. In this work, we introduce a Sn-doped GeSbSeTe (Sn-GSST) material system that enhances SOM performance by reducing trap depth, increasing the population of shallow band-tail trap states, and widening the V<sub>th</sub> margin. These improvements enable stable multibit switching and improved endurance. We evaluate the device’s system-level applicability through binary neural network (BNN) inference on the German Traffic Sign Recognition Benchmark (GTSRB) dataset, where V<sub>th</sub>-induced bit error rate (BER) are modeled using statistical distributions. Sn-GSST devices show significantly lower BER of less than 0.01, leading to improved inference robustness. Finally, Shannon entropy-based error correction code (ECC) analysis confirms that the reduced BER of Sn-GSST leads to lower redundancy overhead and higher inference efficiency. This study demonstrates how material-level engineering can directly translate to system-level reliability and performance in neuromorphic memory applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Sn-Doped selector-only memory with stable threshold voltage margin for robust binary neural network inference

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月19日

查看全文
  • Hyun Kyu Seo,
  • Jaeho Jung,
  • Jae-Seung Jeong,
  • Min Hyuk Park,
  • Gun Hwan Kim,
  • Min Kyu Yang

摘要

With the rise of data-centric applications such as edge AI and neuromorphic computing, there is increasing demand for memory solutions that overcome the limitations of conventional nonvolatile devices. Selector-only memory (SOM), which stores data through threshold voltage (Vth) modulation in chalcogenide-based selector materials, offers a compact and scalable alternative. However, narrow read window margins and Vth drift remain major reliability concerns. In this work, we introduce a Sn-doped GeSbSeTe (Sn-GSST) material system that enhances SOM performance by reducing trap depth, increasing the population of shallow band-tail trap states, and widening the Vth margin. These improvements enable stable multibit switching and improved endurance. We evaluate the device’s system-level applicability through binary neural network (BNN) inference on the German Traffic Sign Recognition Benchmark (GTSRB) dataset, where Vth-induced bit error rate (BER) are modeled using statistical distributions. Sn-GSST devices show significantly lower BER of less than 0.01, leading to improved inference robustness. Finally, Shannon entropy-based error correction code (ECC) analysis confirms that the reduced BER of Sn-GSST leads to lower redundancy overhead and higher inference efficiency. This study demonstrates how material-level engineering can directly translate to system-level reliability and performance in neuromorphic memory applications.