.png){kind=icon}
返回
GEBA: Gradient-Error-Based Approximation of Activation Functions
.png){kind=icon}
PRE
AI
DOI：10.1109/JETCAS.2023.3328890.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Computing-in-memory (CIM) macros aiming at accelerating deep learning operations at low power need activation function (AF) units on the same die to reduce their host-dependency. Versatile CIM macros need to include reconfigurable AF units at high precision and high efficiency in hardware usage. To this end, we propose the gradient-error-based approximation (GEBA) of AFs, which approximates various types of AFs in discrete input domains at high precision. GEBA reduces the approximation error by ca. 49.7%, 67.3%, 81.4%, 60.1% (for sigmoid, tanh, GELU, swish in FP32), compared with the uniform input-based approximation using the same memory as GEBA.
Keyword:
Table lookup
Hardware
Computational modeling
Approximation error
Organizations
Load modeling
Memory management
Activation function
activation function approximation
computing-in-memory
gradient-error-based approximation
lookup table
期刊
IF:
3.8
论文数:
1.4K
被引数:
2.8K
机构
引用论文
Types of Parent Verbal Responsiveness That Predict Language in Young Children With Autism Spectrum Disorder预测自闭症谱系障碍幼儿语言的父母言语反应类型
OAAI
.png){kind=icon}
OAAI分享收藏
分享收藏分享收藏Optimal Weight-Splitting in Resistive Random Access Memory-Based Computing-in-Memory Macros基于电阻式随机存取存储器的计算内存宏中的最佳权重分配OAAI
OAAI分享收藏
查看更多内容