Apple Inc.

Hanlin Goh

Nitish Srivastava

Ruslan Salakhutdinov

Erdrin Azemi

Joseph Yitan Cheng

Yichuan Tang

Bradley William Griffin

Cuneyt Oncel Tuzel

Joshua M Susskind

Kaan Emre Dogrusoz

Chen Huang

Shuangfei Zhai

Walter A Talbott

Joseph Y Cheng

Helen Y Weng

Matthias R Hohmann

The present application relates to apparatus, systems, and methods to perform subject-aware self-supervised learning of a machine-learning model for classification of data, such as classification of biosignals.

Subject-aware contrastive learning for biosignals

A method is provided that includes receiving biosignal data measured from a user, encoding the biosignal data into a vector, and generating, using a generative model, an image based on the vector. The generated image is provided for display.

Visualization of biosignals using machine-learning generated content

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.

Attention free transformer

Techniques are disclosed for defining a training data set to include biosignals and categorical labels representative of a context. For example, a categorical label may indicate whether a user was performing a difficult or easy mental task while the biosignal was being recorded. A set of first layers in a neural network can be trained using a portion of the training data set associated with a first set of users and at least one second layer can be trained using a portion of the training data set associated with a particular other user. The neural network can then be used to process other biosignals from the particular other user to generate predicted categorical context labels.

Machine learning configurations modeled using contextual categorical labels for biosignals

A method includes defining a geometric capsule that is interpretable by a capsule neural network, wherein the geometric capsule includes a feature representation and a pose. The method also includes determining multiple viewpoints relative to the geometric capsule and determining a first appearance representation of the geometric capsule for each of the multiple viewpoints. The method also includes determining a transform for each of the multiple viewpoints that moves each of the multiple viewpoints to a respective transformed viewpoint and determining second appearance representations that each correspond to one of the transformed viewpoints. The method also includes combining the second appearance representations to define an agreed appearance representation. The method also includes updating the feature representation for the geometric capsule based on the agreed appearance representation.

Encoding three-dimensional data for processing by capsule neural networks

A method includes obtaining a two-dimensional image, obtaining a two-dimensional image annotation that indicates presence of an object in the two-dimensional image, obtaining three-dimensional sensor information, generating a top-down representation of the three-dimensional sensor information, and obtaining a top-down annotation that indicates presence of the object in the top-down representation. The method also includes determining a bottom surface of a three-dimensional cuboid based on map information, determining a position, a length, a width, and a yaw rotation of the three-dimensional cuboid based on the top-down annotation, and determining a height of the three-dimensional cuboid based on a two-dimensional image annotation, and the position, the length, the width, and the yaw rotation of the three-dimensional cuboid.

Three-dimensional object estimation using two-dimensional annotations

A method includes obtaining a two-dimensional image, obtaining a two-dimensional image annotation that indicates presence of an object in the two-dimensional image, determining a location proposal based on the two-dimensional image annotation, determining a classification for the object, determining an estimated size for the object based on the classification for the object, and defining a three-dimensional cuboid for the object based on the location proposal and the estimated size.

Growing community of inventors

Sunnyvale, CA, United States of America

Hanlin Goh