Work

Alternating Greedy Schedules: Enabling Low-Bitwidth Accumulation of Dot Products in Neural Network Computations

Year: 2025

Type: conference-paper

Source: IEEE International Symposium on Circuits and Systems proceedings

DOI: 10.1109/iscas56072.2025.11044071

Authors: Vikas Natesh, H.T. Kung

Institution: Harvard University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: closed

Funder: Air Force Research Laboratory

OpenAlex ID: W4411726835

FWCI: 1.57

Cites: 7

Cited by: 2

Related to: 10