What is it about?
We developed a more efficient way to perform Booth multiplication in neural networks using a special type of memory called MRAM. By using this technique, we were able to make neural networks power efficient, which is important for applications like image recognition and language processing.
Featured Image
Photo by Slejven Djurakovic on Unsplash
Read the Original
This page is a summary of: An In-memory Booth Multiplier Based on Non-volatile Memory for Neural Network Applications, December 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3565478.3572534.
You can read the full text:
Contributors
The following have contributed to this page
