activity
20162020
most citedPyramid Vector Quantization and Bit Level Sparsity in Weights for Efficient Neural Networks Inference

1 citations · 1 across the 2 of their papers we have counts for

collaborators

3 papers

cs.CV2020

A MAC-less Neural Inference Processor Supporting Compressed, Variable Precision Weights

Vincenzo Liguori

This paper introduces two architectures for the inference of convolutional neural networks (CNNs). Both architectures exploit weight sparsity and compression to reduce computationa…

cs.CV2019★ 1 cited

Pyramid Vector Quantization and Bit Level Sparsity in Weights for Efficient Neural Networks Inference

Vincenzo Liguori

This paper discusses three basic blocks for the inference of convolutional neural networks (CNNs). Pyramid Vector Quantization (PVQ) is discussed as an effective quantizer for CNNs…

cs.CV2016

Vector Quantization for Machine Vision

Vincenzo Liguori

This paper shows how to reduce the computational cost for a variety of common machine vision tasks by operating directly in the compressed domain, particularly in the context of ha…