Search Results for author:
Found 5 papers, 4 papers with code
CTMQ: Cyclic Training of Convolutional Neural Networks with Multiple Quantization Steps
In each quantization step, the trained weights of a model are used to initialize the weights of the next model with the quantization bit depth reduced by one.
PLAM: a Posit Logarithm-Approximate Multiplier
The Posit Number System was introduced in 2017 as a replacement for floating-point numbers.
The Effects of Approximate Multiplication on Convolutional Neural Networks
The approximate multiplication can reduce the cost of the underlying circuits so that CNN inferences can be performed more efficiently in hardware accelerators.
Deep PeNSieve: A deep learning framework based on the posit number system
The Posit Number System (PNS) was introduced by John L. Gustafson in 2017.
Template-Based Posit Multiplication for Training and Inferring in Neural Networks
Synthesis results are shown to compare with the floating point multiplication offered by FloPoCo as well.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
