C
Chas Leichner
Researcher at Google
Publications - 3
Citations - 38
Chas Leichner is an academic researcher from Google. The author has contributed to research in topics: Quantization (physics) & Artificial neural network. The author has an hindex of 1, co-authored 3 publications receiving 14 citations.
Papers
More filters
Journal ArticleDOI
High-resolution specificity profiling and off-target prediction for site-specific DNA recombinases
Jeffrey L. Bessen,Jeffrey L. Bessen,Jeffrey L. Bessen,Lena K. Afeyan,Lena K. Afeyan,Lena K. Afeyan,Vlado Dančík,Luke W. Koblan,Luke W. Koblan,Luke W. Koblan,David B. Thompson,David B. Thompson,Chas Leichner,Paul A. Clemons,David R. Liu,David R. Liu,David R. Liu +16 more
TL;DR: Rec-seq is described, a method for revealing the DNA specificity determinants and potential off-target substrates of SSRs in a comprehensive and unbiased manner and is established as a high-resolution method for rapidly characterizing theDNA specificity of recombinases with single-nucleotide resolution.
Proceedings ArticleDOI
Pareto-Optimal Quantized ResNet Is Mostly 4-bit
AmirAli Abdolrashidi,Lisa Wang,Shivani Agrawal,Jonathan Malmaud,Oleg Rybakov,Chas Leichner,Lukasz Lew +6 more
TL;DR: In this paper, the effects of quantization on inference cost-quality tradeoff curves were investigated using ResNet as a case study and quantization-aware training was used to achieve state-of-the-art results on ImageNet.
Posted Content
Pareto-Optimal Quantized ResNet Is Mostly 4-bit
AmirAli Abdolrashidi,Lisa Wang,Shivani Agrawal,Jonathan Malmaud,Oleg Rybakov,Chas Leichner,Lukasz Lew +6 more
TL;DR: In this article, the effects of quantization on inference cost-quality tradeoff curves were investigated using ResNet as a case study, and quantization-aware training achieved state-of-the-art results on ImageNet for 4-bit ResNet-50.