Hardware-Efficient Activation Approximation based on Error-Sensitivity Analysis for Deep Neural Networks
Juhyuk Ahn, Kwangrae Kim, Chanhoon Kim, Soomin Rho, Ki-Seok Chung · Asia Conference on Machine Learning and Computing (ACMLC) · 2025
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Asia Conference on Machine Learning and Computing (ACMLC) · OpenAlex · conference-paper · 2025
Abstract
Implementing hardware units for non-linear activation functions is challenging due to their distinct characteristics. While approximation methods offer a promising solution, conventional approaches such as CORDIC and Chebyshev polynomials suffer from high latency, and piecewise linear (PWL) methods require large lookup tables (LUTs) to achieve acceptable accuracy. Furthermore, existing methods often overlook the varying impact of approximation errors across input regions.
Open the resolved locator · 10.1145/3772673.3772698
Metadata licence: OpenAlex metadata (CC0)