Search International and National Patent Collections

1. (WO2018102016) TRAINING AND/OR USING NEURAL NETWORK MODELS TO GENERATE INTERMEDIARY OUTPUT OF A SPECTRAL IMAGE

Pub. No.:    WO/2018/102016    International Application No.:    PCT/US2017/054183
Publication Date: Fri Jun 08 01:59:59 CEST 2018 International Filing Date: Fri Sep 29 01:59:59 CEST 2017
IPC: G06N 3/04
Applicants: GOOGLE INC.
Inventors: GORBAN, Alexander
Title: TRAINING AND/OR USING NEURAL NETWORK MODELS TO GENERATE INTERMEDIARY OUTPUT OF A SPECTRAL IMAGE
Abstract:
Systems, methods, and computer readable media related to training and/or using a neural network model. The trained neural network model can be utilized to generate (e.g., over a hidden layer) a spectral image based on a regular image, and to generate output indicative of one or more features present in the generated spectral image (and present in the regular image since the spectral image is generated based on the regular image). As one example, a regular image may be applied as input to the trained neural network model, a spectral image generated over multiple layers of the trained neural network model based on the regular image, and output generated over a plurality of additional layers based on the spectral image. The generated output may be indicative of various features, depending on the training of the additional layers of the trained neural network model.