Kurt Keutzer

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

The Landscape of Parallel Computing Research: A View from Berkeley

FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

A Survey of Quantization Methods for Efficient Neural Network Inference

SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

System-level design: orthogonalization of concerns and platform-based design

SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and &lt;0.5MB model size

DenseNet: Implementing Efficient ConvNet Descriptor Pyramids

A view of the parallel computing landscape

SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

DAGON: technology binding and local optimization by DAG matching