Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering

May 1, 2022·

Thorir Mar Ingolfsson

,

Mark Vero

,

Xiaying Wang

Lorenzo Lamberti

,

Luca Benini

,

Matteo Spallanzani

· 0 min read

Type

Conference paper

Publication

Proceedings of the 19th ACM International Conference on Computing Frontiers

Last updated on May 1, 2022

Lorenzo Lamberti

Authors

Lorenzo Lamberti

Postdoc Researcher

Lorenzo Lamberti Postdoc at ETH Zurich and IDSIA. His research revolves around miniaturized robotics and edge devices.

← Tiny-PULP-Dronets: Squeezing Neural Networks for Faster and Lighter Inference on Multi-Tasking Autonomous Nano-Drones June 1, 2022

Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks December 1, 2021 →