Invention Grant
- Patent Title: Batch normalization layers
-
Application No.: US17156453Application Date: 2021-01-22
-
Publication No.: US11893485B2Publication Date: 2024-02-06
- Inventor: Sergey Ioffe , Corinna Cortes
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/04 ; G06N3/084 ; G06F18/10 ; G06F18/2415 ; G06V10/70 ; G06V10/82

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using a neural network system that includes a batch normalization layer. One of the methods includes receiving a respective first layer output for each training example in the batch; computing a plurality of normalization statistics for the batch from the first layer outputs; normalizing each component of each first layer output using the normalization statistics to generate a respective normalized layer output for each training example in the batch; generating a respective batch normalization layer output for each of the training examples from the normalized layer outputs; and providing the batch normalization layer output as an input to the second neural network layer.
Public/Granted literature
- US20210224653A1 BATCH NORMALIZATION LAYERS Public/Granted day:2021-07-22
Information query