Apple Inc.

Blue River Technology Inc.

Other

Nicholas Elia Apostoloff

Russell Y Webb

Barry-John Theobald

Lee Kamp Redden

Siddharth Khullar

Abhishek A Sharma

Jerremy Holland

Tomas Jon Pfister

Tai-Peng Tian

Garrett L Weinberg

Luca Zappella

Jamie R Lesser

Xavier Suau Cuadros

Moussa Doumbouya

Amruta Pai

Nataniel Ruiz Gutierrez

Melanie S Subbiah

Megan M Maher

Katherine Elaine Metcalf

In some examples, an individually-pruned neural network can estimate blood pressure from a seismocardiogram (SCG). In some examples, a baseline model can be constructed by training the model with SCG data and blood pressure measurement from a plurality of subjects. One or more filters (e.g., the filters in the top layer of the network) can be ranked by separability, which can be used to prune the model for each unseen user that uses the model thereafter, for example. In some examples, individuals can use individually-pruned models to calculate blood pressure using SCG data without corresponding blood pressure measurements.

Interpretable neural networks for cuffless blood pressure estimation

A method includes obtaining a speech proficiency value indicator indicative of a speech proficiency value associated with a user of the electronic device. The method further includes in response to determining that the speech proficiency value satisfies a threshold proficiency value: displaying training text via the display device; obtaining, from the audio sensor, speech data associated with the training text, wherein the speech data is characterized by the speech proficiency value; determining, using a speech classifier, one or more speech characterization vectors for the speech data based on linguistic features within the speech data; and adjusting one or more operational values of the speech classifier based on the one or more speech characterization vectors and the speech proficiency value.

Interactive reading assistant

A method includes, while displaying a first set of text content via a display device, determining an engagement value that characterizes a level of user engagement with respect to the first set of text content. The method includes, in accordance with a determination that the engagement value satisfies a threshold, replacing the first set of text content with a second set of text content via the display device. The first set of text content is different from the second set of text content. The method includes in accordance with a determination that the engagement value does not satisfy the threshold, maintaining display of the first set of text content via the display device.

Methods and apparatus are disclosed for interpreting a deep neural network (DNN) using a Semantic Coherence Analysis (SCA)-based interpretation technique. In embodiments, a multi-layered DNN that was trained for one task is analyzed using the SCA technique to select one layer in the DNN that produces salient features for another task. In embodiments, the DNN layers are tested with test samples labeled with a set of concept labels. The output features of a DNN layer are gathered and analyzed according to the concepts. In embodiments, the output is scored with a semantic coherence score, which indicates how well the layer separates the concepts, and one layer is selected from the DNN based on its semantic coherence score. In some embodiments, a support vector machine (SVM) or additional neural network may be added to the selected layer and trained to generate classification results based on the outputs of the selected layer.

Semantic coherence analysis of deep neural networks

A method includes obtaining user input interaction data. The user input interaction data includes one or more user interaction input values respectively obtained from the corresponding one or more input devices. The user input interaction data includes a word combination. The method includes generating a user interaction-style indicator value corresponding to the word combination in the user input interaction data. The user interaction-style indicator value is a function of the word combination and a portion of the one or more user interaction input values. The method includes determining, using a semantic text analyzer, a semantic assessment of the word combination in the user input interaction data based on the user interaction-style indicator value and a natural language assessment of the word combination. The method includes generating a response to the user input interaction data according to the user interaction-style indicator value and the semantic assessment of the word combination.

Generating responses to user interaction data based on user interaction-styles

Controlling an automated agent in an environment includes obtaining high-quality data regarding a current state of the automated agent; identifying a behavior model; determining a trajectory estimate for the automated agent based on the current state of the automated agent and the behavior model; determining a final trajectory for the automated agent using the trajectory estimate; and controlling the automated agent according to the final trajectory.

Multimodal input processing system

One aspect of the disclosure is a non-transitory computer-readable storage medium including program instructions. Operations performed by execution of the program instructions include obtaining an input image that depicts a face of a subject, having an initial facial expression and an initial pose, determining a reference shape description based on the input image, determining a target shape description based on the reference shape description, a facial expression difference, and a pose difference, generating a rendered target shape image using the target shape description, and generating an output image based on the input image and the rendered target shape using an image generator, wherein the output image is a simulated image of the subject of the input image that has a final expression that is based on the initial facial expression and the facial expression difference, and a final pose that is based on the initial pose and the pose difference.

Face image generation with pose and expression control

Modifying operation of an intelligent agent in response to facial expressions and/or emotions.

Intelligent software agent

A method includes displaying a first set of text content characterized by a first difficulty level. The method includes obtaining speech data associated with the first set of text content. The method includes determining linguistic feature(s) within the speech data. The method includes in response to completion of the speech data, determining a reading proficiency value associated with the first set of text content and based on the linguistic feature(s). The method includes in accordance with determining the reading proficiency value satisfies change criteria, changing a difficulty level for a second set of text content. After changing the difficulty level, the second set of text content corresponds to a second difficulty level different from the first difficulty level. The method includes in accordance with determining the reading proficiency value does not satisfy the change criteria, maintaining the second set of text content at the first difficulty level.

A method that includes obtaining real training samples that include real images that depict real objects, obtaining simulated training samples that include simulated images that depict simulated objects, defining a training dataset that includes at least some of the real training samples and at least some of the simulated training samples, and training a machine learning model to detect subject objects in unannotated input images using the training dataset.

Training with simulated images

A technique for generating virtual models of plants in a field is described. Generally, this includes recording images of plants in-situ; generating point clouds from the images; generating skeleton segments from the point cloud; classifying a subset of skeleton segments as unique plant features using the images; and growing plant skeletons from skeleton segments classified as unique plant feature. The technique may be used to generate a virtual model of a single, real plant, a portion of a real plant field, and/or the entirety of the real plant field. The virtual model can be analyzed to determine or estimate a variety of individual plant or plant population parameters, which in turn can be used to identify potential treatments or thinning practices, or predict future values for yield, plant uniformity, or any other parameter can be determined from the projected results based on the virtual model.

Growing community of inventors

San Jose, CA, United States of America

Nicholas Elia Apostoloff