Search Results for author: Freddy Gabbay

Found 2 papers, 1 papers with code

Post-Training Sparsity-Aware Quantization

1 code implementation NeurIPS 2021 Gil Shomron, Freddy Gabbay, Samer Kurzum, Uri Weiser

Moreover, instead of quantizing activation-by-activation to 4 bits, we focus on pairs of 8-bit activations and examine whether one of the two is equal to zero.

Quantization

HCM: Hardware-Aware Complexity Metric for Neural Network Architectures

no code implementations19 Apr 2020 Alex Karbachevsky, Chaim Baskin, Evgenii Zheltonozhskii, Yevgeny Yermolin, Freddy Gabbay, Alex M. Bronstein, Avi Mendelson

Convolutional Neural Networks (CNNs) have become common in many fields including computer vision, speech recognition, and natural language processing.

Quantization speech-recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.