Nicholas M Johnston

US Patent:

20200311548, Oct 1, 2020

Filed:

Oct 29, 2019

Appl. No.:

16/666689

Inventors:

- Mountain View CA, US
Saurabh Singh - Mountain View CA, US
Johannes Balle - San Francisco CA, US
Sami Ahmad Abu-El-Haija - East Palo Alto CA, US
Nicholas Johnston - San Jose CA, US
George Dan Toderici - Mountain View CA, US

International Classification:

G06N 3/08
G06N 3/063
G06K 9/62
G06F 17/15

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving, by a neural network (NN), a dataset for generating features from the dataset. A first set of features is computed from the dataset using at least a feature layer of the NN. The first set of features i) is characterized by a measure of informativeness; and ii) is computed such that a size of the first set of features is compressible into a second set of features that is smaller in size than the first set of features and that has a same measure of informativeness as the measure of informativeness of the first set of features. The second set of features if generated from the first set of features using a compression method that compresses the first set of features to generate the second set of features.

US Patent:

20200234126, Jul 23, 2020

Filed:

Jan 23, 2020

Appl. No.:

16/751175

Inventors:

- Mountain View CA, US
David Marwood - Sunnyvale CA, US
Shumeet Baluja - La Jolla CA, US
Nicholas Johnston - San Jose CA, US

International Classification:

G06N 3/08
G06N 3/04
G06F 1/03

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing a network input using a neural network to generate a network output for the network input. One of the methods includes maintaining, for each of the plurality of neural network layers, a respective look-up table that maps each possible combination of a quantized input index and a quantized weight index to a multiplication result; and generating a network output from a network input, comprising, for each of the neural network layers: receiving data specifying a quantized input to the neural network layer, the quantized input comprising a plurality of quantized input values; and generating a layer output for the neural network layer from the quantized input to the neural network layer using the respective look-up table for the neural network layer.

US Patent:

20200111238, Apr 9, 2020

Filed:

May 29, 2018

Appl. No.:

16/617484

Inventors:

- Mountain View CA, US
Damien Vincent - Zurich, CH
David Charles Minnen - Mountain View CA, US
Saurabh Singh - Mountain View CA, US
Sung Jin Hwang - Mountain View CA, US
Nicholas Johnston - San Jose CA, US
Joel Eric Shor - Mountain View CA, US
George Dan Toderici - Mountain View CA, US

International Classification:

G06T 9/00
G06T 3/40
G06T 7/00
G06N 3/04
G06N 3/08

Abstract:

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image compression and reconstruction. An image encoder system receives a request to generate an encoded representation of an input image that has been partitioned into a plurality of tiles and generates the encoded representation of the input image. To generate the encoded representation, the system processes a context for each tile using a spatial context prediction neural network that has been trained to process context for an input tile and generate an output tile that is a prediction of the input tile. The system determines a residual image between the particular tile and the output tile generated by the spatial context prediction neural network by process the context for the particular tile and generates a set of binary codes for the particular tile by encoding the residual image using an encoder neural network.

US Patent:

20200027247, Jan 23, 2020

Filed:

Jul 18, 2019

Appl. No.:

16/515586

Inventors:

- Mountain View CA, US
Saurabh Singh - Mountain View CA, US
Johannes Balle - San Francisco CA, US
Troy Chinen - Newark CA, US
Sung Jin Hwang - Mountain View CA, US
Nicholas Johnston - San Jose CA, US
George Dan Toderici - Mountain View CA, US

International Classification:

G06T 9/00
G06T 3/40
G06N 3/08
G06N 20/00
G06F 17/18

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for compressing and decompressing data. In one aspect, a method comprises: processing data using an encoder neural network to generate a latent representation of the data; processing the latent representation of the data using a hyper-encoder neural network to generate a latent representation of an entropy model; generating an entropy encoded representation of the latent representation of the entropy model; generating an entropy encoded representation of the latent representation of the data using the latent representation of the entropy model; and determining a compressed representation of the data from the entropy encoded representations of: (i) the latent representation of the data and (ii) the latent representation of the entropy model used to entropy encode the latent representation of the data.

US Patent:

20190356931, Nov 21, 2019

Filed:

May 16, 2019

Appl. No.:

16/413992

Inventors:

- Mountain View CA, US
Michele Covell - Woodside CA, US
Shumeet Baluja - La Jolla CA, US
Nicholas Milo Johnston - San Jose CA, US
Pascal Massimino - Orsay, FR

International Classification:

H04N 19/90
H04N 19/186
H04N 19/176
G06T 9/00

Abstract:

An encoder system can include a pixel grid generator to receive an image having a first dimension, generate a grid having a second dimension, add a plurality of points to positions on the grid, and map a plurality of pixels of the image to the plurality of points. The encoder system can include a color module to assign a color to each of the plurality of points using a color table, a triangulation module to generate a plurality of vertices based on the plurality of points and triangulate the grid using the vertices, and a compression module to compress the vertices as a set of compressed vertex positions and a set of vertex colors.

US Patent:

20150256618, Sep 10, 2015

Filed:

Mar 6, 2014

Appl. No.:

14/198971

Inventors:

- Mountain View CA, US
Nicholas Johnston - San Jose CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

H04L 29/08
H04L 29/06

Abstract:

A reading group that is associated with an ebook is defined, the reading group including a master device and one or more follower devices. A synchronization command is received from the master device to synchronize the reading location of the one or more follower devices to a read section, the read section specifying a portion of the ebook. The synchronization command is provided to the one or more follower devices, and in response to receiving the synchronization command the one or more follower devices are configured to present the ebook in accordance with the read section.

US Patent:

20150170664, Jun 18, 2015

Filed:

Mar 14, 2013

Appl. No.:

13/803497

Inventors:

Ryan P. DOHERTY - Mountain View CA, US
Nicholas M. JOHNSTON - Mountain View CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G10L 21/00

Abstract:

A device may receive, from a peripheral device, information for controlling the peripheral device. The information for controlling the peripheral device may include information identifying a voice command associated with the peripheral device and information identifying a function corresponding to the voice command. The device may receive, from a user, the voice command. The device may cause the peripheral device to perform the function based on receiving the voice command.

US Patent:

20140249811, Sep 4, 2014

Filed:

Mar 1, 2013

Appl. No.:

13/781853

Inventors:

Google Inc. - , US
Nicholas Johnston - San Jose CA, US

Assignee:

Google Inc. - Mountain View CA

International Classification:

G10L 15/05

US Classification:

704231, 704251

Abstract:

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for classifying voice inputs. The methods, systems, and apparatus include actions of providing an answer to a first voice input from a user and receiving visual or audio data corresponding to a second voice input. Further actions include classifying the second voice input as a follow on request to the first voice input or as deliberation on the answer, based on the visual data or the audio data. Additionally, the actions include determining whether to provide a response to the second voice input based on the classification of the second voice input.