公开(公告)号：US20200327450A1

公开(公告)日：2020-10-15

申请号：US16384738

申请日：2019-04-15

Applicant: Apple Inc.

Inventor： Chen HUANG ,  Joshua M. SUSSKIND ,  Carlos GUESTRIN

IPC: G06N20/00

Abstract: The subject technology trains, for a first set of iterations, a first machine learning model using a loss function with a first set of parameters. The subject technology determines, by a second machine learning model, a state of the first machine learning model corresponding to the first set of iterations. The subject technology determines, by the second machine learning model, an action for updating the loss function based on the state of the first machine learning model. The subject technology updates, by the second machine learning model, the loss function based at least in part on the action, where the updated loss function includes a second set of parameters corresponding to a change in values of the first set of parameters. The subject technology trains, for a second set of iterations, the first machine learning model using the updated loss function with the second set of parameters.

公开(公告)号：US20210099731A1

公开(公告)日：2021-04-01

申请号：US16835724

申请日：2020-03-31

Applicant: Apple Inc.

Inventor： Shuangfei ZHAI ,  Joshua M. SUSSKIND

IPC: H04N19/625 ,  G06N20/00

Abstract: Techniques for coding sets of images with neural networks include transforming a first image of a set of images into coefficients with an encoder neural network, encoding a group of the coefficients as an integer patch index into coding table of table entries each having vectors of coefficients, and storing a collection of patch indices as a first coded image. The encoder neural network may be configured with encoder weights determined by jointly with corresponding decoder weights of a decoder neural network on the set of images.

公开(公告)号：US20220292781A1

公开(公告)日：2022-09-15

申请号：US17689851

申请日：2022-03-08

Applicant: Apple Inc.

Inventor： Miguel Angel BAUTISTA MARTIN ,  Nitish SRIVASTAVA ,  Joshua M. SUSSKIND ,  Terrance DEVRIES

IPC: G06T19/00 ,  G06T19/20 ,  G06T15/55

Abstract: Implementations of the subject technology relate to generative scene networks (GSNs) that are able to generate realistic scenes that can be rendered from a free moving camera at any location and orientation. A GSN may be implemented using a global generator and a locally conditioned radiance field. GSNs may employ a spatial latent representation as conditioning for a grid of locally conditioned radiance fields, and may be trained using an adversarial learning framework. Inverting a GSN may allow free navigation of a generated scene conditioned on one or more observations.

公开(公告)号：US20220108212A1

公开(公告)日：2022-04-07

申请号：US17308033

申请日：2021-05-04

Applicant: Apple Inc.

Inventor： Shuangfei ZHAI ,  Walter A. TALBOTT ,  Nitish SRIVASTAVA ,  Chen HUANG ,  Hanlin GOH ,  Joshua M. SUSSKIND

IPC: G06N20/00 ,  G06N5/04 ,  G06F17/16 ,  G06F40/58 ,  G06T3/40

Abstract: Attention-free transformers are disclosed. Various implementations of attention-free transformers include a gating and pooling operation that allows the attention-free transformers to provide comparable or better results to those of a standard attention-based transformer, with improved efficiency and reduced computational complexity with respect to space and time.