Qualcomm incorporated (20250131258). COMPRESSION OF SPARSE DEEP CONVOLUTIONAL NETWORK WEIGHTS
COMPRESSION OF SPARSE DEEP CONVOLUTIONAL NETWORK WEIGHTS
Organization Name
Inventor(s)
Rexford Hill of San Diego CA US
COMPRESSION OF SPARSE DEEP CONVOLUTIONAL NETWORK WEIGHTS
This abstract first appeared for US patent application 20250131258 titled 'COMPRESSION OF SPARSE DEEP CONVOLUTIONAL NETWORK WEIGHTS
Original Abstract Submitted
the present disclosure describes methods, computer-readable media, and apparatuses for operating neural networks. for example, an apparatus may receive a set of sparse weight vectors. the apparatus may perform a sparse computation based on the set of sparse weight vectors. the apparatus may combine sparse weight vectors in response to determining a combined time to perform respective numbers of mac operations for the sparse weight vectors satisfies a threshold number of clock cycles. the apparatus may operate a neural network based at least in part on one or more partial sums produced in performing the sparse computation.
