Huan Jen Wang

20220335257, Oct 20, 2022

Apr 15, 2021

17/231015

- San Francisco CA, US
Huan Wang - Fremont CA, US
Caiming Xiong - Menlo Park CA, US

G06K 9/62
G06N 3/08

A system uses a neural network to detect anomalies in time series data. The system trains the neural network for a fixed number of iterations using data from a time window of the time series. The system uses the loss value at the end of the fixed number of iterations for identifying anomalies in the time series data. For a time window, the system initializes the neural network to random values and trains the neural network for a fixed number of iterations using the data of the time window. After the fixed number of iterations, the system compares the loss values for various data points to a threshold value. Data points having loss value exceeding a threshold are identified as anomalous data points.

20230105322, Apr 6, 2023

Jan 28, 2022

17/588066

- San Francisco CA, US
Devansh Arpit - Pacifica CA, US
Huan Wang - Fremont CA, US
Caiming Xiong - Menlo Park CA, US

G06N 3/08
G06N 3/04

Embodiments described herein provide a system and method for extracting information. The system receives, via a communication interface, a dataset of a plurality of data samples. The system determines, in response to an input data sample from the dataset, a set of feature vectors via a plurality of pre-trained feature extractors, respectively. The system retrieves a set of memory bank vectors that correspond to the input data sample. The system, generates, via a plurality of Multi-Layer-Perceptrons (MLPs), a mapped set of representations in response to an input of the set of memory bank vectors, respectively. The system determines a loss objective between the set of feature vectors and the combination of the mapped set of representations and a network of layers in the MLP. The system updates, the parameters of the plurality of MLPs and the parameters of the memory bank vectors by minimizing the computed loss objective.

20180183618, Jun 28, 2018

Dec 23, 2016

15/389958

- Menlo Park CA, US
Andrew Cairns Moxon - San Francisco CA, US
Andrew Yaoshu Song - San Francisco CA, US
Huan Yan Wang - Belmont CA, US
Viswanath Poosala - Cupertino CA, US

H04L 12/18
H04L 12/58
H04L 29/08

Techniques for group message thread link joining are described. In one embodiment, an apparatus may comprise a user interface component operative to receive a join invitation link at a messaging client on the client device, the join invitation link comprising a thread invitation identifier, the thread invitation identifier identifying a group message thread on a messaging system; and receive a group join command at the messaging client; and a client messaging component operative on the processor circuit to add a user account to the group message thread with the messaging system in response to receiving the group join command by identifying the group message thread to the messaging system using the thread invitation identifier. Other embodiments are described and claimed.

20180183619, Jun 28, 2018

Dec 23, 2016

15/389998

- Menlo Park CA, US
Andrew Cairns Moxon - San Francisco CA, US
Andrew Yaoshu Song - San Francisco CA, US
Huan Yan Wang - Belmont CA, US
Viswanath Poosala - Cupertino CA, US

H04L 12/18
H04L 12/58
H04L 29/08
H04L 29/06

Techniques for group message thread link administration are described. In one embodiment, an apparatus may comprise a client front-end component operative to receive a join invitation command associated with a group message thread from an administrator client device, the group message thread associated with a message thread identifier, the message thread identifier identifying the group message thread on a messaging system; and send a join invitation link to the administrator client device; and a group management component operative to generate a join invitation link in response to the join invitation command, the join invitation link comprising a thread invitation identifier, wherein the thread invitation identifier is a hash of the message thread identifier. Other embodiments are described and claimed.