Li Y He

7238292, Jul 3, 2007

Jul 30, 2004

10/909224

Li He - Fremont CA, US
Ming Zhao - Fremont CA, US
Yining Hu - Fremont CA, US

Western Digital (Fremont), Inc. - Fremont CA

B44C 1/00
G11B 5/127

216 22, 216 41, 216 49, 216 59, 216 67, 216 88, 2960303, 2960312, 20419234

A head including a write element for writing data to a magnetic media, and methods for its production are provided. A write element of the invention includes one or more of a recessed first pole, a heat sink layer, and a shortened yoke length. A method of the invention provides forming an anti-reflective layer before forming a mask layer. During photolithography the anti-reflective layer suppresses undesirable reflections off of features, such as vertical sidewalls, that otherwise limit how closely to such features portions of the mask layer can be formed.

7379269, May 27, 2008

Jul 30, 2004

10/903140

Mohamad T. Krounbi - San Jose CA, US
Li He - Fremont CA, US
Ming Zhao - Fremont CA, US
Yining Hu - Fremont CA, US

Western Digital (Fremont), LLC - Fremont CA

G11B 5/147

360126

A head including a write element for writing data to a magnetic media, and methods for its production are provided. A write element of the invention includes one or more of a recessed first pole, a heat sink layer, and a shortened yoke length. A method of the invention provides forming an anti-reflective layer before forming a mask layer. During photolithography the anti-reflective layer suppresses undesirable reflections off of features, such as vertical sidewalls, that otherwise limit how closely to such features portions of the mask layer can be formed.

7552523, Jun 30, 2009

Jul 1, 2005

11/172778

Li He - Fremont CA, US
Jun Liu - San Ramon CA, US
Danning Yang - Fremont CA, US
Yining Hu - Fremont CA, US

Western Digital (Fremont), LLC - Fremont CA

G11B 5/127
H04R 31/00

2960316, 2960313, 2960314, 2960315, 2960318, 216 62, 216 66, 216 67, 360122, 360317, 451 5, 451 41

A method and system for manufacturing a perpendicular magnetic recording transducer by a process that includes plating is described. The method and system include forming a chemical mechanical planarization (CMP) uniformity structure around a perpendicular magnetic recording pole. The CMP uniformity structure has a height substantially equal to a desired pole height. The method and system also include fabricating an insulator on the CMP uniformity structure and performing a CMP to remove a portion of the insulator. The CMP exposes a portion of the perpendicular magnetic recording pole and planarizes an exposed surface of the perpendicular magnetic recording transducer.

20190294923, Sep 26, 2019

Mar 19, 2019

16/357360

- Milpitas CA, US
Li He - San Jose CA, US
Sankar Venkataraman - Milpitas CA, US
Michael Kowalski - Scotts Valley CA, US
Arjun Hegde - Newark CA, US

G06K 9/62
G06N 20/00
G06F 3/0482
G06T 7/00

Methods and systems for training a machine learning model using synthetic defect images are provided. One system includes one or more components executed by one or more computer subsystems. The one or more components include a graphical user interface (GUI) configured for displaying one or more images for a specimen and image editing tools to a user and for receiving input from the user that includes one or more alterations to at least one of the images using one or more of the image editing tools. The component(s) also include an image processing module configured for applying the alteration(s) to the at least one image thereby generating at least one modified image and storing the at least one modified image in a training set. The computer subsystem(s) are configured for training a machine learning model with the training set in which the at least one modified image is stored.

20190287230, Sep 19, 2019

Aug 21, 2018

16/106341

- Milpitas CA, US
Li He - San Jose CA, US
Sankar Venkataraman - Milpitas CA, US

G06T 7/00

Autoencoder-based, semi-supervised approaches are used for anomaly detection. Defects on semiconductor wafers can be discovered using these approaches. The model can include a variational autoencoder, such as a one that includes ladder networks. Defect-free or clean images can be used to train the model that is later used to discover defects or other anomalies.

20160358041, Dec 8, 2016

Jan 29, 2016

15/010887

- Milpitas CA, US
Li He - San Jose CA, US
Oksen Baris - San Francisco CA, US
Harsh Sinha - Santa Clara CA, US

G06K 9/62
G06T 7/00

Defect classification includes acquiring one or more images of a specimen including multiple defects, grouping the defects into groups of defect types based on the attributes of the defects, receiving a signal from a user interface device indicative of a first manual classification of a selected number of defects from the groups, generating a classifier based on the first manual classification and the attributes of the defects, classifying, with the classifier, one or more defects not manually classified by the manual classification, identifying the defects classified by the classifier having the lowest confidence level, receiving a signal from the user interface device indicative of an additional manual classification of the defects having the lowest confidence level, determining whether the additional manual classification identifies one or more additional defect types not identified in the first manual classification, and iterating the procedure until no new defect types are found.