公开(公告)号：US20220236971A1

公开(公告)日：2022-07-28

申请号：US17159524

申请日：2021-01-27

Applicant: X Development LLC

Inventor： Qianyu Zhang ,  Bin Ni ,  Rishabh Singh ,  Olivia Hatalsky

IPC: G06F8/41 ,  G06F8/71 ,  G06F8/36 ,  G06F8/34

Abstract: Implementations are described herein for adapting existing source code snippets to new contexts. In various implementations, a command may be detected to incorporate an existing source code snippet into destination source code. An embedding may be generated based on the existing source code snippet, e.g., by processing the existing source code snippet using an encoder. The destination source code may be processed to identify one or more decoder constraints. Subject to the one or more decoder constraints, the embedding may be processed using a decoder to generate a new version of the existing source code snippet that is adapted to the destination source code.

公开(公告)号：US11169786B2

公开(公告)日：2021-11-09

申请号：US16781344

申请日：2020-02-04

Applicant: X Development LLC

Inventor： Rohan Badlani ,  Owen Lewis ,  Georgios Evangelopoulos ,  Olivia Hatalsky ,  Bin Ni

IPC: G06F9/44 ,  G06F8/41 ,  G06N20/00 ,  G06F8/73 ,  G06F8/38 ,  G06N3/04

Abstract: Implementations are described herein for generating embeddings of source code using both the language and graph domains, and leveraging combinations of these semantically-rich and structurally-informative embeddings for various purposes. In various implementations, tokens of a source code snippet may be applied as input across a sequence-processing machine learning model to generate a plurality of token embeddings. A graph may also be generated based on the source code snippet. A joint representation may be generated based on the graph and the incorporated token embeddings. The joint representation generated from the source code snippet may be compared to one or more other joint representations generated from one or more other source code snippets to make a determination about the source code snippet.

公开(公告)号：US20210240453A1

公开(公告)日：2021-08-05

申请号：US16781344

申请日：2020-02-04

Applicant: X Development LLC

Inventor： Rohan Badlani ,  Owen Lewis ,  Georgios Evangelopoulos ,  Olivia Hatalsky ,  Bin Ni

IPC: G06F8/41 ,  G06F8/73 ,  G06N20/00 ,  G06N3/04 ,  G06F8/38

Abstract: Implementations are described herein for generating embeddings of source code using both the language and graph domains, and leveraging combinations of these semantically-rich and structurally-informative embeddings for various purposes. In various implementations, tokens of a source code snippet may be applied as input across a sequence-processing machine learning model to generate a plurality of token embeddings. A graph may also be generated based on the source code snippet. A joint representation may be generated based on the graph and the incorporated token embeddings. The joint representation generated from the source code snippet may be compared to one or more other joint representations generated from one or more other source code snippets to make a determination about the source code snippet.

公开(公告)号：US11636349B2

公开(公告)日：2023-04-25

申请号：US16829107

申请日：2020-03-25

Applicant: X Development LLC

Inventor： Sarah Ann Laszlo ,  Matthew Sibigtroth ,  Bin Ni

IPC: G06N3/10 ,  G06N3/04 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying one or more regions of a brain of a biological organism that are predicted to be functionally-specialized for performing a task. In one aspect, a method comprises: obtaining data defining a synaptic connectivity graph representing synaptic connectivity between neurons in the brain of the biological organism; identifying a plurality of sub-graphs of the synaptic connectivity graph; determining, for each sub-graph of the plurality of sub-graphs, a performance measure characterizing a performance of a neural network having a neural network architecture that is specified by the sub-graph in accomplishing the task; and determining, based on the performance measures, that one or more sub-graphs of the plurality of sub-graphs correspond to regions of the brain of the biological organism that are predicted to be functionally-specialized for performing the task.

公开(公告)号：US11461081B2

公开(公告)日：2022-10-04

申请号：US17159524

申请日：2021-01-27

Applicant: X Development LLC

Inventor： Qianyu Zhang ,  Bin Ni ,  Rishabh Singh ,  Olivia Hatalsky

IPC: G06F9/44 ,  G06F8/41 ,  G06F8/34 ,  G06F8/36 ,  G06F8/71 ,  G06F16/00 ,  G06F16/242 ,  G06N3/08 ,  G06N3/04

Abstract: Implementations are described herein for adapting existing source code snippets to new contexts. In various implementations, a command may be detected to incorporate an existing source code snippet into destination source code. An embedding may be generated based on the existing source code snippet, e.g., by processing the existing source code snippet using an encoder. The destination source code may be processed to identify one or more decoder constraints. Subject to the one or more decoder constraints, the embedding may be processed using a decoder to generate a new version of the existing source code snippet that is adapted to the destination source code.

公开(公告)号：US11243746B2

公开(公告)日：2022-02-08

申请号：US16458713

申请日：2019-07-01

Applicant: X Development LLC

Inventor： Georgios Evangelopoulos ,  Olivia Hatalsky ,  Bin Ni ,  Qianyu Zhang

IPC: G06F9/44 ,  G06F8/33 ,  G06N3/08 ,  G06F8/40

Abstract: Techniques are described herein for using artificial intelligence to “learn,” statistically, a target programming style that is imposed in and/or evidenced by a code base. Once the target programming style is learned, it can be used for various purposes. In various implementations, one or more generative adversarial networks (“GANs”), each including a generator machine learning model and a discriminator machine learning model, may be trained to facilitate learning and application of target programming style(s). In some implementations, the discriminator(s) and/or generator(s) may operate on graphical input, and may take the form of graph neural networks (“GNNs”), graph attention neural networks (“GANNs”), graph convolutional networks (“GCNs”), etc., although this is not required.

公开(公告)号：US11064284B2

公开(公告)日：2021-07-13

申请号：US16235360

申请日：2018-12-28

Applicant: X Development LLC

Inventor： Jason Rugolo ,  Bin Ni ,  Cyrus Behroozi

IPC: H04R1/10 ,  G10K11/178 ,  H04R3/00 ,  H04S7/00 ,  H04R5/033

Abstract: An in-ear device includes a housing shaped to hold the in-ear device in an ear of a user, and an audio package, disposed in the housing, to emit augmented sound. A first set of one or more microphones is positioned to receive external sound, and a controller is coupled to the audio package and the first set of one or more microphones. The controller includes a low-latency audio processing path, digital control parameters, and logic that when executed by the controller causes the in-ear device to perform operations. The operations may include receiving the external sound with the first set of one or more microphones to generate a low-latency sound signal; augmenting the low-latency sound signal by passing the low-latency sound signal through the low-latency audio processing path to produce an augmented sound signal; and outputting, with the audio package, the augmented sound based on the augmented sound signal.

公开(公告)号：US20210004210A1

公开(公告)日：2021-01-07

申请号：US16458713

申请日：2019-07-01

Applicant: X Development LLC

Inventor： Georgios Evangelopoulos ,  Olivia Hatalsky ,  Bin Ni ,  Qianyu Zhang

IPC: G06F8/33 ,  G06F8/40 ,  G06N3/08

Abstract: Techniques are described herein for using artificial intelligence to “learn,” statistically, a target programming style that is imposed in and/or evidenced by a code base. Once the target programming style is learned, it can be used for various purposes. In various implementations, one or more generative adversarial networks (“GANs”), each including a generator machine learning model and a discriminator machine learning model, may be trained to facilitate learning and application of target programming style(s). In some implementations, the discriminator(s) and/or generator(s) may operate on graphical input, and may take the form of graph neural networks (“GNNs”), graph attention neural networks (“GANNs”), graph convolutional networks (“GCNs”), etc., although this is not required.

公开(公告)号：US20200371778A1

公开(公告)日：2020-11-26

申请号：US16418767

申请日：2019-05-21

Applicant: X Development LLC

Inventor： Bin Ni ,  Benoit Schillings ,  Georgios Evangelopoulos ,  Olivia Hatalsky ,  Qianyu Zhang ,  Grigory Bronevetsky

IPC: G06F8/71 ,  G06N3/08

Abstract: Implementations are described herein for automatically identifying, recommending, and/or effecting changes to a legacy source code base by leveraging knowledge gained from prior updates made to other similar legacy code bases. In some implementations, data associated with a first version source code snippet may be applied as input across a machine learning model to generate a new source code embedding in a latent space. Reference embedding(s) may be identified in the latent space based on their distance(s) from the new source code embedding in the latent space. The reference embedding(s) may be associated with individual changes made during the prior code base update(s). Based on the identified one or more reference embeddings, change(s) to be made to the first version source code snippet to create a second version source code snippet may be identified, recommended, and/or effected.

公开(公告)号：US20200211277A1

公开(公告)日：2020-07-02

申请号：US16235092

申请日：2018-12-28

Applicant: X Development LLC

Inventor： Jason Rugolo ,  Bin Ni ,  Daniel George

IPC: G06T17/05 ,  G06N20/00 ,  G06N3/08

Abstract: A system to optically measure an ear includes a controller with logic that when executed by the controller causes the system to perform operations. Operations may include capturing the one or more images of the ear using the one or more image sensors, and generating image data from the one or more images. 3D keypoints of the ear are calculated from the image data, and a 3D model of the ear is generated using the 3D keypoints.