公开(公告)号：US20250094780A1

公开(公告)日：2025-03-20

申请号：US18468203

申请日：2023-09-15

Applicant: QUALCOMM Incorporated

Inventor： Kartikeya BHARDWAJ ,  Piero ZAPPI ,  Paul Nicholas WHATMOUGH ,  Christopher LOTT ,  Viswanath GANAPATHY ,  Chirag Sureshbhai PATEL ,  Joseph Binamira SORIAGA

IPC: G06N3/0464

Abstract: Certain aspects provide techniques and apparatuses for efficiently processing inputs in a neural network using multiple receptive field sizes. An example method includes partitioning a first input into a first set of channels and a second set of channels. At a first layer of a neural network, the first set of channels and the second set of channels are convolved into a first output having a smaller dimensionality a dimensionality of the first input. The first set of channels and the first output are concatenated into a second input. The second input is convolved into a second output via a second layer of the neural network, wherein the second output merges a first receptive field generated by the first layer with a larger second receptive field generated by the second layer. One or more actions are taken based on at least one of the first output and the second output.

公开(公告)号：US20250148358A1

公开(公告)日：2025-05-08

申请号：US18504117

申请日：2023-11-07

Applicant: QUALCOMM Incorporated

Inventor： Zhuojin LI ,  Hsin-Pai CHENG ,  Hong CAI ,  Sweta PRIYADARSHI ,  Kartikeya BHARDWAJ ,  Viswanath GANAPATHY ,  Chirag Sureshbhai PATEL ,  Fatih Murat PORIKLI

IPC: G06N20/00

Abstract: A processor-implemented method for training-free architecture searching for a transformer model includes generating a set of transformer model candidates for a target device. Each transformer model candidate of the set of transformer model candidates is initialized with random weights. A set of data samples are randomly sampled to produce random data samples for inputting at each transformer model candidate. An attention confidence score is computed for each transformer model candidate based on the random data samples and the random weights. A transformer model candidate for the target device is selected based on the attention confidence score.