scispace - formally typeset
A

Amir Gholami

Researcher at University of California, Berkeley

Publications -  80
Citations -  4702

Amir Gholami is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 26, co-authored 68 publications receiving 2795 citations. Previous affiliations of Amir Gholami include University of Texas at Austin.

Papers
More filters
Posted ContentDOI

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

Spyridon Bakas, +438 more
- 05 Nov 2018 - 
TL;DR: This study assesses the state-of-the-art machine learning methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018, and investigates the challenge of identifying the best ML algorithms for each of these tasks.
Journal ArticleDOI

Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT

Sheng Shen, +7 more
TL;DR: This work performs an extensive analysis of fine-tuned BERT models using second order Hessian information, and uses the results to propose a novel method for quantizing BERT Models to ultra low precision, which is based on a new group-wise quantization scheme and Hessian-based mix-precision method.
Proceedings ArticleDOI

HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision

Zhen Dong, +4 more
TL;DR: Hessian AWare Quantization (HAWQ), a novel second-order quantization method that allows for the automatic selection of the relative quantization precision of each layer, based on the layer's Hessian spectrum, is introduced.
Proceedings ArticleDOI

ZeroQ: A Novel Zero Shot Quantization Framework

Yaohui Cai, +5 more
TL;DR: THE AUTHORS' enables mixed-precision quantization without any access to the training or validation data, and it can finish the entire quantization process in less than 30s, which is very low computational overhead.
Proceedings ArticleDOI

SqueezeNext: Hardware-Aware Neural Network Design

Amir Gholami, +7 more
TL;DR: SqueezeNext as discussed by the authors is a new family of neural network architectures whose design was guided by considering previous architectures such as SqueezeNet, as well as by simulation results on a neural network accelerator.