Invention Grant
- Patent Title: Generating an output for a neural network output layer
-
Application No.: US15385642Application Date: 2016-12-20
-
Publication No.: US10373049B2Publication Date: 2019-08-06
- Inventor: Reginald Clifford Young
- 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: G06E1/00
- IPC: G06E1/00 ; G06E3/00 ; G06F15/18 ; G06G7/00 ; G06N3/04 ; G06N3/063 ; G06N7/00

Abstract:
Systems, methods, and apparatus, including computer programs encoded on a computer storage medium for processing a network input through a neural network having one or more initial neural network layers followed by a softmax output layer. In one aspect, the methods include obtaining a layer output generated by the one or more initial neural network layers and processing the layer output through the softmax output layer to generate a neural network output. Processing the layer output through the softmax output layer includes determining, for each possible output value, a number of occurrences in the layer output values; for each possible output value occurring in the layer output values, determining a respective exponentiation measure; determining a normalization factor for the layer output by combining the exponentiation measures in accordance with the number of occurrences of the possible output values; and determining, for each of layer output values, a softmax probability value.
Public/Granted literature
- US20180174022A1 GENERATING AN OUTPUT FOR A NEURAL NETWORK OUTPUT LAYER Public/Granted day:2018-06-21
Information query