...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Proceedings of the IEEE >Bioinspired Programming of Memory Devices for Implementing an Inference Engine
【24h】

Bioinspired Programming of Memory Devices for Implementing an Inference Engine

机译：受存储启发的存储设备编程，以实现推理引擎

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Cognitive tasks are essential for the modern applications of electronics, and rely on the capability to perform inference. The Von Neumann bottleneck is an important issue for such tasks, and emerging memory devices offer an opportunity to overcome this issue by fusing computing and memory, in nonvolatile instant systems. A vision for accomplishing this is to use brain-inspired architectures, which excel at inference and do not differentiate between computing and memory. In this work, we use a neuroscience-inspired model of learning, spike-timing-dependent plasticity, to develop a bioinspired approach for programming memory devices, which naturally gives rise to an inference engine. The method is then adapted to different memory devices, including multivalued memories (cumulative memristive device, phase-change memory) and stochastic binary memories (conductive bridge memory, spin transfer torque magnetic tunnel junction). By means of system-level simulations, we investigate several applications, including image recognition and pattern detection within video and auditory data. We compare the results of the different devices. Stochastic binary devices require the use of redundancy, the extent of which depends tremendously on the considered task. A theoretical analysis allows us to understand how the various devices differ, and ties the inference engine to the machine learning algorithm of expectation–maximization. Monte Carlo simulations demonstrate an exceptional robustness of the inference engine with respect to device variations and other issues. A theoretical analysis explains the roots of this robustness. These results highlight a possible new bioinspired paradigm for programming emerging memory devices, allowing the natural learning of a complex inference engine. The physics of the memory devices plays an active role. The results open the way for a reinvention of the role of memory, when solving inference tasks.
机译：认知任务对于电子的现代应用是必不可少的，并且依赖于执行推理的能力。冯·诺依曼瓶颈是执行此类任务的重要问题，新兴的存储设备为非易失性即时系统中的计算和内存融合提供了克服此问题的机会。实现这一目标的愿景是使用受大脑启发的架构，该架构擅长推理，并且不会在计算和内存之间进行区分。在这项工作中，我们使用了受神经科学启发的学习模型（依赖于尖峰时序的可塑性）来开发一种受生物启发的方法来对存储设备进行编程，这自然会产生一个推理引擎。然后，该方法适用于不同的存储设备，包括多值存储（累积忆阻设备，相变存储）和随机二进制存储（导电桥存储，自旋传递转矩磁隧道结）。通过系统级仿真，我们研究了几种应用，包括视频和听觉数据中的图像识别和模式检测。我们比较了不同设备的结果。随机二进制设备需要使用冗余，冗余的程度在很大程度上取决于所考虑的任务。理论分析使我们能够了解各种设备的差异，并将推理引擎与期望最大化的机器学习算法联系起来。蒙特卡洛仿真证明了推理机在设备变化和其他问题方面的出色鲁棒性。理论分析解释了这种鲁棒性的根源。这些结果突显了一种可能的，新的，受生物启发的范例，可以对新兴的存储设备进行编程，从而自然地学习复杂的推理引擎。存储设备的物理学起着积极的作用。结果为解决推理任务时重塑记忆的作用开辟了道路。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号