all AI news
QONNX: Representing Arbitrary-Precision Quantized Neural Networks. (arXiv:2206.07527v3 [cs.LG] UPDATED)
June 27, 2022, 1:11 a.m. | Alessandro Pappalardo, Yaman Umuroglu, Michaela Blott, Jovan Mitrevski, Ben Hawks, Nhan Tran, Vladimir Loncar, Sioni Summers, Hendrik Borras, Jules Mu
stat.ML updates on arXiv.org arxiv.org
We present extensions to the Open Neural Network Exchange (ONNX) intermediate
representation format to represent arbitrary-precision quantized neural
networks. We first introduce support for low precision quantization in existing
ONNX-based quantization formats by leveraging integer clipping, resulting in
two new backward-compatible variants: the quantized operator format with
clipping and quantize-clip-dequantize (QCDQ) format. We then introduce a novel
higher-level ONNX format called quantized ONNX (QONNX) that introduces three
new operators -- Quant, BipolarQuant, and Trunc -- in order to represent
uniform …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Scientist (m/f/x/d)
@ Symanto Research GmbH & Co. KG | Spain, Germany
Enterprise Data Quality, Senior Analyst
@ Toyota North America | Plano
Data Analyst & Audit Management Software (AMS) Coordinator
@ World Vision | Philippines - Home Working
Product Manager Power BI Platform Tech I&E Operational Insights
@ ING | HBP (Amsterdam - Haarlerbergpark)
Sr. Director, Software Engineering, Clinical Data Strategy
@ Moderna | USA-Washington-Seattle-1099 Stewart Street
Data Engineer (Data as a Service)
@ Xplor | Atlanta, GA, United States