Junjie J Su

US Patent:

20200105338, Apr 2, 2020

Filed:

Aug 27, 2019

Appl. No.:

16/553109

Inventors:

- Taipei City, TW
MINGZHE JIANG - San Diego CA, US
JUNJIE SU - San Diego CA, US
Chun-Chen Liu - San Diego CA, US

International Classification:

G11C 11/412
H01L 29/792
H01L 27/088
G11C 11/419

Abstract:

A memory cell includes a first charge trap transistor and a second charge trap transistor. The first charge trap transistor has a substrate, a first terminal coupled to a first bitline, a second terminal coupled to a signal line, a control terminal coupled to a wordline, and a dielectric layer formed between the substrate of the first charge trap transistor and the control terminal of the first charge trap transistor. The second charge trap transistor has a substrate, a first terminal coupled to the signal line, a second terminal coupled to a second bitline, a control terminal coupled to the wordline, and a dielectric layer between the substrate of the second charge trap transistor and the control terminal of the second charge trap transistor. Charges are either trapped to or detrapped from the dielectric layer of the first charge trap transistor when writing data to the memory cell.

US Patent:

20200097816, Mar 26, 2020

Filed:

Aug 27, 2019

Appl. No.:

16/551743

Inventors:

- Taipei City, TW
Bike Xie - San Diego CA, US
Hsiang-Tsun Li - Taichung City, TW
Junjie Su - San Diego CA, US
Chun-Chen Liu - San Diego CA, US

International Classification:

G06N 3/08
G06N 3/063
G06F 7/544

Abstract:

A system for operating a floating-to-fixed arithmetic framework includes a floating-to-fix arithmetic framework on an arithmetic operating hardware such as a central processing unit (CPU) for computing a floating pre-trained convolution neural network (CNN) model to a dynamic fixed-point CNN model. The dynamic fixed-point CNN model is capable of implementing a high performance convolution neural network (CNN) on a resource limited embedded system such as mobile phone or video cameras.

US Patent:

20200082160, Mar 12, 2020

Filed:

Aug 1, 2019

Appl. No.:

16/528642

Inventors:

- Taipei City, TW
Bike Xie - San Diego CA, US
JUNJIE SU - San Diego CA, US

International Classification:

G06K 9/00
G01N 21/359
G06N 3/02

Abstract:

A face recognition module includes a near infrared flash, a master near infrared camera, an artificial intelligence NIR image model, an artificial intelligence original image model, and an artificial intelligence fusion model. The NIR flash flashes near infrared light. The master near infrared camera captures a NIR image. The artificial intelligence NIR image model processes the NIR image to generate NIR features. The artificial intelligence original image model processes a 2 dimensional second camera image to generate face features or color features. The artificial intelligence fusion model generates 3 dimensional face features, a depth map and an object's 3 dimensional model according to the NIR features, the face features and the color features.

US Patent:

20200082247, Mar 12, 2020

Filed:

Aug 29, 2019

Appl. No.:

16/554634

Inventors:

- Taipei City, TW
JUNJIE SU - San Diego CA, US
Chun-Chen Liu - San Diego CA, US

International Classification:

G06N 3/04
G06N 3/08

Abstract:

A searching framework system includes an arithmetic operating hardware. When operating the searching framework system, input data and reconfiguration parameters are inputted to an automatic architecture searching framework of the arithmetic operating hardware. The automatic architecture searching framework then executes arithmetic operations to search for an optimized convolution neural network (CNN) model and outputs the optimized CNN model.

US Patent:

20190378013, Dec 12, 2019

Filed:

Jun 6, 2018

Appl. No.:

16/001923

Inventors:

- San Diego CA, US
JUNJIE SU - San Diego CA, US
Bike Xie - San Diego CA, US
Chun-Chen Liu - San Diego CA, US

International Classification:

G06N 3/08
G06N 3/04
G06N 3/063

Abstract:

A self-tuning model compression methodology for reconfiguring a Deep Neural Network includes: receiving a DNN model and a data set, wherein the DNN includes an input layer, at least one hidden layer and an output layer, and said at least one hidden layer and the output layer of the DNN model includes a plurality of neurons; compressing the DNN model into a reconfigured model according to the data set, wherein the reconfigured model includes an input layer, at least one hidden layer and an output layer, and said at least one hidden layer and the output layer of the reconfigured model includes a plurality of neurons, and a size of the reconfigured model is smaller than a size of the DNN model; and executing the reconfigured model on a user terminal for an end-user application.

US Patent:

20190370656, Dec 5, 2019

Filed:

Jan 24, 2019

Appl. No.:

16/255850

Inventors:

- Taipei City, TW
JUNJIE SU - San Diego CA, US
BODONG ZHANG - Shenyang City, CN
Chun-Chen Liu - San Diego CA, US

International Classification:

G06N 3/08
G06N 3/04

Abstract:

A method of pruning a batch normalization layer from a pre-trained deep neural network model is proposed. The pre-trained deep neural network model is inputted as a candidate model. The candidate model is pruned by removing the at least one batch normalization layer from the candidate model to form a pruned candidate model only when the at least one batch normalization layer is connected to and adjacent to a corresponding linear operation layer. The corresponding linear operation layer may be at least one of a convolution layer, a dense layer, a depthwise convolution layer, and a group convolution layer. Weights of the corresponding linear operation layer are adjusted to compensate for the removal of the at least one batch normalization. The pruned candidate model is then output and utilized for inference.

US Patent:

20190370658, Dec 5, 2019

Filed:

Apr 18, 2019

Appl. No.:

16/388840

Inventors:

- Taipei City, TW
JUNJIE SU - San Diego CA, US
JIE WU - San Diego CA, US
BODONG ZHANG - Shenyang City, CN
Chun-Chen Liu - San Diego CA, US

International Classification:

G06N 3/08
G06N 20/10

Abstract:

A method of compressing a pre-trained deep neural network model includes inputting the pre-trained deep neural network model as a candidate model. The candidate model is compressed by increasing sparsity of the candidate, removing at least one batch normalization layer present in the candidate model, and quantizing all remaining weights into fixed-point representation to form a compressed model. Accuracy of the compressed model is then determined utilizing an end-user training and validation data set. Compression of the candidate model is repeated when the accuracy improves. Hyper parameters for compressing the candidate model are adjusted, then compression of the candidate model is repeated when the accuracy declines. The compressed model is output for inference utilization when the accuracy meets or exceeds the end-user performance metric and target.