Sheng Cheng Li

US Patent:

8229566, Jul 24, 2012

Filed:

Jun 25, 2008

Appl. No.:

12/146176

Inventors:

Sheng Li - Bronx NY, US

International Classification:

A61B 5/08
A61N 1/36

US Classification:

607 48, 600529

Abstract:

Methods and devices are provided such that electrical stimulation can be delivered to a patient's skeletal muscles in response to certain respiratory signals, such as when voluntary breathing is detected.

US Patent:

20200327446, Oct 15, 2020

Filed:

Apr 10, 2019

Appl. No.:

16/380566

Inventors:

- San Jose CA, US
Sheng Li - Suwanee GA, US
Handong Zhao - San Jose CA, US
Sungchul Kim - San Jose CA, US

Assignee:

Adobe Inc. - San Jose CA

International Classification:

G06N 20/00

Abstract:

Techniques are disclosed for the generation of adversarial training data through sequence perturbation, for a deep learning network to perform event sequence analysis. A methodology implementing the techniques according to an embodiment includes applying a long short-term memory attention model to an input data sequence to generate discriminative sequence periods and attention weights associated with the discriminative sequence periods. The attention weights are generated to indicate the relative importance of data in those discriminative sequence periods. The method further includes generating perturbed data sequences based on the discriminative sequence periods and the attention weights. The generation of the perturbed data sequences employs selective filtering or conservative adversarial training, to preserve perceptual similarity between the input data sequence and the perturbed data sequences. The input data sequence may be created by vectorizing a temporal input data stream comprising words, symbols, and the like, into a multidimensional vectorized numerical data sequence format.