Apple inc. (20250156706). PSEUDO RANDOM PROJECTION FOR MACHINE LEARNING COMPRESSION
PSEUDO RANDOM PROJECTION FOR MACHINE LEARNING COMPRESSION
Organization Name
Inventor(s)
Saman Naderiparizi of Seattle WA US
David Harrison of Seattle WA US
Mahyar Najibikohnehshahri of Santa Clara CA US
Mohammad Rastegari of Kirkland WA US
Rasoul Shafipour of Bellevue WA US
PSEUDO RANDOM PROJECTION FOR MACHINE LEARNING COMPRESSION
This abstract first appeared for US patent application 20250156706 titled 'PSEUDO RANDOM PROJECTION FOR MACHINE LEARNING COMPRESSION
Original Abstract Submitted
the subject technology provides for pseudo random projection for machine learning compression. an apparatus determines a first data structure comprising pseudo random values and a second data structure comprising one or more learned values based on a target compression ratio of a first dimension associated with a first weight matrix to a second dimension. the apparatus generates the second weight matrix comprising the second data structure and a seed value associated with the first data structure. the second weight matrix may be generated based at least in part on the pseudo random values and the one or more learned values. the second weight matrix is a compressed version of the first weight matrix based on the target compression ratio. the apparatus also trains a neural network with the second weight matrix to produce a trained machine learning model.
(Ad) Transform your business with AI in minutes, not months
Trusted by 1,000+ companies worldwide
