TIME SERIES DATA ADAPTATION AND SENSOR FUSION SYSTEMS, METHODS, AND APPARATUS

WIPO Patent Application WO/2017/122784

A1

Systems, methods, and apparatus for time series data adaptation, including sensor fusion, are disclosed. For example, a system includes a variational inference machine, a sequential data forecast machine including a hidden state, and a machine learning model. The sequential data forecast machine exports a version of the hidden state. The variational inference machine receives as inputs time series data and the version of the hidden state, and outputs a time dependency infused latent distribution. The sequential data forecast machine obtains the version of the hidden state, receives as inputs the time series data and the time dependency infused latent distribution, and updates the hidden state based on the time series data, the time dependency infused latent distribution, and the version of the hidden state to generate a second version of the hidden state. The time dependency infused latent distribution is input into the machine learning model, which outputs a result.

JPH0444158	METHOD AND DEVICE FOR PROCESSING INFORMATION
JP7466784	Training a neural network using graph-based temporal classification
WO/2022/211375	VIDEO CODING METHOD AND DEVICE USING DEEP LEARNING-BASED IN-LOOP FILTER FOR INTER-PREDICTION

CLAYTON B JUSTIN (US)
OKANOHARA DAISUKE (JP)
HIDO SHOHEI (US)

PCT/JP2017/001033

July 20, 2017

January 13, 2017

Click for automatic bibliography generation  

PREFERRED NETWORKS INC (JP)

G06N3/04

US5956702A

1999-09-21

BAYER, JUSTIN ET AL.: "Variational inference of latent state sequences using Recurrent Networks", ARXIV, 6 June 2014 (2014-06-06), pages 1 - 12, Retrieved from the Internet > [retrieved on 20170313]

SUDO Yutaka et al. (JP)

View/Download PDF      PDF Help

Previous Patent: INTERDENTAL BRUSH

Next Patent: SYSTEMS AND METHODS FOR MULTIMODAL GENERATIVE MACHINE LEARNING