Invention Application
- Patent Title: GRANULAR NEURAL NETWORK ARCHITECTURE SEARCH OVER LOW-LEVEL PRIMITIVES
-
Application No.: US17827362Application Date: 2022-05-27
-
Publication No.: US20220383119A1Publication Date: 2022-12-01
- Inventor: David Richard So , Quoc V. Le, Jr. , Hanxiao Liu , Wojciech Andrzej Manke , Zihang Dai , Noam M. Shazeer
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Main IPC: G06N3/08
- IPC: G06N3/08

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing a machine learning task on a network input to generate a network output. One of the systems includes an attention neural network configured to perform the machine learning task. The attention neural network includes one or more attentions layers that each include a squared ReLU activation layer, a depth-wise convolution layer, or both.
Public/Granted literature
- US3228991A Process and catalyst for the preparation of methyl-1, 3-cyclopentadiene Public/Granted day:1966-01-11
Information query