Infox: An energy-efficient reram accelerator design with information-lossless low-bit adcs
ReRAM-based accelerators have shown great potential in neural network acceleration via in-
memory analog computing. However, high-precision analog-to-digital converters (ADCs) …
memory analog computing. However, high-precision analog-to-digital converters (ADCs) …
[HTML][HTML] 近似计算新范式在深度学习加速系统中的应用及研究进展
龚宇， 王丽萍， 王佑， 刘伟强 - 电子与信息学报, 2023 - jeit.ac.cn
深度学习已经成为当前人工智能技术中最为重要的算法之一. 随着应用场景不断扩展,
深度学习硬件规模越来越大, 计算复杂度呈现数量级提升趋势, 对加速系统提出了极高能效需求 …
深度学习硬件规模越来越大, 计算复杂度呈现数量级提升趋势, 对加速系统提出了极高能效需求 …
AKGF: Automatic Kernel Generation for DNN on CPU-FPGA
D Dong, H Jiang, B Diao - The Computer Journal, 2024 - academic.oup.com
While tensor accelerated compilers have proven effective in deploying deep neural
networks (DNN) on general-purpose hardware, optimizing for FPGA remains challenging …
networks (DNN) on general-purpose hardware, optimizing for FPGA remains challenging …
[HTML][HTML] Application and Research Progress of Approximate Computing as a New Computing Paradigm in AI Acceleration Systems
G Yu, W Liping, W You, LIU Weiqiang - 电子与信息学报, 2023 - jeit.ac.cn
Deep learning has emerged as one of the most important algorithms in artificial intelligence.
With the increasing application scenarios, the hardware scales for deep learning are …
With the increasing application scenarios, the hardware scales for deep learning are …
Sensitivity mode for an audio spotting system
SM Kaskari - US Patent 11,823,707, 2023 - Google Patents
An audio spotting system configured for various operating modes including a regular mode
and sensitivity mode is described. An example cascade audio spotting system may include a …
and sensitivity mode is described. An example cascade audio spotting system may include a …