公开(公告)号：US20240412076A1

公开(公告)日：2024-12-12

申请号：US18330253

申请日：2023-06-06

Applicant: QUALCOMM Incorporated

Inventor： Anuj GUPTA ,  Himanshu UPRETI ,  Venkata Subba Dheeraj GATTUPALLI ,  Vinayak Narayan BADDI ,  Prasanna Ashish BISWAS ,  Mohit SHARMA

IPC: G06N3/0985

Abstract: A processor-implemented method of pre-processing for deep neural network compilation comprising receiving a representation of an artificial neural network (ANN) model. An operator embedding is generated to represent operators of the ANN model in an embedding space. A graph neural network (GNN) processes the operator embedding to generate a graph embedding corresponding to the ANN model according to a learned distance metric. The GNN determines a set of hyperparameters for the ANN model based on the graph embedding.

公开(公告)号：US20240412035A1

公开(公告)日：2024-12-12

申请号：US18500014

申请日：2023-11-01

Applicant: QUALCOMM Incorporated

Inventor： Anuj GUPTA ,  Himanshu UPRETI ,  Venkata Subba Dheeraj GATTUPALLI ,  Vinayak Narayan BADDI ,  Prasanna Ashish BISWAS ,  Mohit SHARMA ,  Anusha V.S BHAMIDIPATI ,  Piyush SHARMA

IPC: G06N3/042

Abstract: A processor-implemented method of pre-processing for deep neural network compilation comprising receiving a representation of an artificial neural network (ANN) model. The ANN includes multiple nodes coupled by edges. Position information is determined for each node of the ANN. An operator embedding is generated to represent operators of the ANN model in an embedding space based on the position information. A graph neural network (GNN) processes the operator embedding to generate a graph embedding corresponding to the ANN model according to a learned distance metric and based on the position information. The GNN determines a set of hyperparameters for the ANN model based on the graph embedding.