18504016. FLEXIBLE MACHINE LEARNING MODEL COMPRESSION (GOOGLE LLC)
FLEXIBLE MACHINE LEARNING MODEL COMPRESSION
Organization Name
Inventor(s)
Aditya Binodkumar Agrawal of Santa Clara CA US
Blake Alan Hechtman of Mountain View CA US
Matthew Leever Hedlund of Sun Prairie WI US
David Alexander Majnemer of Mountain View CA US
Marissa Karen Ikonomidis of Sunnyvale CA US
FLEXIBLE MACHINE LEARNING MODEL COMPRESSION
This abstract first appeared for US patent application 18504016 titled 'FLEXIBLE MACHINE LEARNING MODEL COMPRESSION
Original Abstract Submitted
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compresses a machine learning model having a plurality of parameters. In one aspect, one of the methods includes obtaining trained values of a set of parameters for at least a portion of a machine learning model; identifying one or more dense ranges for the trained values; determining a least number of bits required to represent each trained value within the one or more dense ranges; identifying a second format having a range that is smaller than a range of the first format; and generating a compressed version of the at least a portion of the machine learning model.