DeepAI AI Chat
Log In Sign Up

Deep Learning Training on the Edge with Low-Precision Posits

07/30/2019
by   Hamed F. Langroudi, et al.
0

Recently, the posit numerical format has shown promise for DNN data representation and compute with ultra-low precision ([5..8]-bit). However, majority of studies focus only on DNN inference. In this work, we propose DNN training using posits and compare with the floating point training. We evaluate on both MNIST and Fashion MNIST corpuses, where 16-bit posits outperform 16-bit floating point for end-to-end DNN training.

READ FULL TEXT
08/06/2019

Cheetah: Mixed Low-Precision Hardware Software Co-Design Framework for DNNs on the Edge

Low-precision DNNs have been extensively explored in order to reduce the...
04/19/2018

Minimizing Area and Energy of Deep Learning Hardware Design Using Collective Low Precision and Structured Compression

Deep learning algorithms have shown tremendous success in many recogniti...
04/08/2023

BRAMAC: Compute-in-BRAM Architectures for Multiply-Accumulate on FPGAs

Deep neural network (DNN) inference using reduced integer precision has ...
11/19/2022

Accuracy Boosters: Epoch-Driven Mixed-Mantissa Block Floating-Point for DNN Training

The unprecedented growth in DNN model complexity, size and the amount of...
07/09/2019

Template-Based Posit Multiplication for Training and Inferring in Neural Networks

The posit number system is arguably the most promising and discussed top...