-
公开(公告)号:US20250094793A1
公开(公告)日:2025-03-20
申请号:US18469909
申请日:2023-09-19
Applicant: QUALCOMM Incorporated
Inventor: Manish Kumar SINGH , Tianyu JIANG , Hsin-Pai CHENG , Kartikeya BHARDWAJ , Hong CAI , Mingu LEE , Munawar HAYAT , Christopher LOTT , Fatih Murat PORIKLI
IPC: G06N3/0499
Abstract: A processor-implemented method for image or text processing includes receiving, by an artificial neural network (ANN) model, a set of tokens corresponding to an input. A token interaction block of the ANN model processes the set of tokens according to each channel of the input to generate a spatial mixture of a set of features for each channel of the input. A feed forward network block of the ANN model generates a mixture of channel features based on the spatial mixture of the set of features for each channel of the input. An attention block of the ANN model determines a set of attended features of the mixture of channel features according to a set of attention weights. In turn, the ANN model generates an inference based on the set of attend features of the mixture of channel features.
-
公开(公告)号:US20240428576A1
公开(公告)日:2024-12-26
申请号:US18613263
申请日:2024-03-22
Applicant: QUALCOMM Incorporated
Inventor: Tianyu JIANG , Manish Kumar SINGH , Hsin-Pai CHENG , Hong CAI , Mingu LEE , Kartikeya BHARDWAJ , Christopher LOTT , Fatih Murat PORIKLI
Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. A transformed version of image pixels is accessed as input to an attention layer of a machine learning model. A number of local attention operations to apply, in one transformer, to the transformed version of image pixels is selected based at least in part on a size of the transformed version of image pixels. A transformer output for the attention layer of the machine learning model is generated based on applying the number of local attention operations and at least one global attention operation to the transformed version of image pixels.
-
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.
-
-