Amazon Technologies, Inc.

Play-i, Inc.

Apple Inc.

Enlighted, Inc.

Facebook, Inc.

Wonder Workshop, Inc.

Saurabh Gupta

Vikas Gupta

Leo Parker Dirac

Vineet Khare

Lakshmi Naarayanan Ramakrishnan

Bharathan Balaji

Amin Hani Atrash

Tanuj Mohan

Andrea Olgiati

Andrea Mucignat

Ramyanshu Datta

Sahika Genc

Wei You

Arvind Sowmyan

Raumi Sidki

Kohen Berith Chia

Kunal Mehrotra

Ishaaq Chandy

Aram M Lindahl

Richard Michael Powell

Joseph M Williams

Mikal B Greaves

Sunil Mallya Kasaragod

Wang Chun Leung

Aditya Palnitkar

Leisen Huang

Kevin Liang

Yelin Kim

Shi Bai

Orion Elenzil

Yash Gupta

Sandeep Samdaria

Stefano Stefani

Dilek Zeynep Hakkani-Tur

Yang Liu

Chenlei Guo

Premal Ashar

Mukesh Karki

Xing Fan

Gurumurthy Swaminathan

Anna Chen Santos

Bo Eric Ericsson

Tanya Bansal

Ragav Venkatesan

Arun Babu Nagarajan

Runfei Luo

Thomas Irvine Nelson

Omkar Prabhu

Urvashi Chowdhary

Orchid Majumder

Morelle Sheer Arian

Vikas Deshpande

Joshua Seth Levy

Xiaowen Mao

Sven Cremer

Siddhartha Agarwal

Yijie Zhuang

Xingyuan Wang

Alex Tang

Vidhi Kastuar

John Moretti

Eunah Cho

Zhihan Li

A simulation application container executes a simulation of a system in a simulation environment, through which an agent representing the system uses a reinforcement learning model to operate within the simulation environment. The simulation application container obtains data indicating how the agent performed in the simulation environment and transmits this data to a robot application container. The robot application container uses the data to update the reinforcement learning model and provides the updated reinforcement learning model to perform another iteration of the simulation and continue training the reinforcement learning model.

Simulation modeling exchange

A post-task-completion retention period for which a computing resource is to be retained, without de-activating the resource, on behalf of a set of requesters of machine learning tasks is determined at a machine learning service. A first task, identified at the service prior to expiration of the retention period at a first computing resource at which a second task has completed, is initiated at the first computing resource. In response to obtaining an indication of a third task and determining that a threshold criterion associated with the retention period satisfies a criterion, the third task is initiated at an additional computing resource. The additional computing resource is de-activated after the third task completes, without waiting for the retention period to expire.

Client-configurable retention periods for machine learning service-managed resources

Parameters of a pool of computing resources to be utilized for machine learning tasks from a set of entities are stored, including a category of the computing resources, and a post-task-completion retention period during which, after completion of a task, at least a portion of data stored at the resource is not to be deleted. A compute instance of the pool is assigned to a task requested from the set of entities after determining that one or more configuration settings of the instance satisfy a preference indicated in the request for the task, and that the retention period of the instance relative to a completion of an earlier task on the instance has not expired. A result of the task is stored.

Resource management techniques to reduce startup overhead for machine learning tasks

A machine learning environment utilizing training data generated by customer networks. A reinforcement learning machine learning environment receives and processes training data generated by simulated hosted, or integrated, customer networks. The reinforcement learning machine learning environment corresponds to machine learning clusters that receive and process training data sets provided by the integrated customer networks. The customer networks include an agent process that collects training data and forwards the training data to the machine learning clusters. The machine learning clusters can be configured in a manner to automatically process the training data without requiring additional user inputs or controls to configure the application of the reinforcement learning machine learning processes.

Integrated machine learning training

A method for toy robot programming, the toy robot including a set of sensors, the method including, at a user device remote from the toy robot: receiving sensor measurements from the toy robot during physical robot manipulation; in response to detecting a programming trigger event, automatically converting the sensor measurements into a series of puppeted programming inputs; and displaying graphical representations of the set of puppeted programming inputs on a programming interface application on the user device.

System and method for reinforcing programming education through robotic feedback

A machine learning environment utilizing training data generated by customer environments. A reinforced learning machine learning environment receives and processes training data generated by independently hosted, or decoupled, customer environments. The reinforced learning machine learning environment corresponds to machine learning clusters that receive and process training data sets provided by the decoupled customer environments. The customer environments include an agent process that collects training data and forwards the training data to the machine learning clusters without exposing the customer environment. The machine learning clusters can be configured in a manner to automatically process the training data without requiring additional user inputs or controls to configured the application of the reinforced learning machine learning processes.

Decoupled machine learning training

Techniques for determining and using interaction affinity data are described. Interaction affinity data may indicate a latent affinity between information corresponding to an interaction, such as, intents, entities, device type from which a user input is received, domain, etc. A system may use the interaction affinity data to determine an alternative input representation for a spoken input to cause output of a desired response to the spoken input. The system may also use the interaction affinity data to recommend an action to a user.

Interaction data and processing natural language inputs

Techniques for sequence to sequence (S2S) model building and/or optimization are described. For example, a method of receiving a request to build a sequence to sequence (S2S) model for a use case, wherein the request includes at least a training data set, generating parts of a S2S algorithm based on the at least one use case, determined parameters, and determined hyperparameters, and training a S2S algorithm built from the parts of the S2S algorithm using the training data set to generate the S2S model is detailed.

Building sequence to sequence (S2S) models using previously generated S2S models with similar use cases

Techniques and technologies for providing a fully managed datastore for clients to securely store, discover, retrieve, remove, and share curated data, or features, to develop machine learning (ML) models in an efficient manner. The feature store service may provide clients with the ability to create and store feature groups that include features and associated metadata providing clients with a quick understanding of features so that they may determine which features are suitable for training ML models and/or use with ML models. The feature store service may provide first a data store configured to store the most recent values associated with a feature group, such that client can access the features and utilize ML models to make real-time predictions with low latency and high throughput, and a second datastore configured to store historical values associated with a feature group, such that a client can utilize the features to train ML models.

Fully managed repository to create, version, and share curated data for machine learning development

Techniques for iterative model training and deployment for automated learning systems are described. A method of iterative model training and deployment for automated learning systems comprises generating training data based on inference data, provided by a first version of a model hosted at an endpoint of a machine learning service, and feedback data, received from a client application, using an identifier associated with the inference data and the feedback data, generating a second version of the model using the training data, and deploying the model to the endpoint of the machine learning service.

Iterative model training and deployment for automated learning systems

A robot that is able to move about an environment determines a wait location in the environment to wait at when not otherwise in use. The wait location may be selected based on various factors including position of objects, next scheduled use, previous usage of the robot, availability of wireless connectivity, user traffic patterns, user presence, visibility of the surrounding environment, and so forth. The robot moves to that location and maintains a pose at that location, such as orienting itself to allow onboard sensors a greatest possible view of the environment. If a wait location is occupied, the robot may move to another wait location.

Dynamic wait location for an autonomous mobile device

Described herein is a system for improving sentiment detection and/or recognition using multiple inputs. For example, an autonomously motile device is configured to generate audio data and/or image data and perform sentiment detection processing. The device may process the audio data and the image data using a multimodal temporal attention model to generate sentiment data that estimates a sentiment score and/or a sentiment category. In some examples, the device may also process language data (e.g., lexical information) using the multimodal temporal attention model. The device can adjust its operations based on the sentiment data. For example, the device may improve an interaction with the user by estimating the user's current emotional state, or can change a position of the device and/or sensor(s) of the device relative to the user to improve an accuracy of the sentiment data.

Multimodal sentiment detection

A robot moves about an environment and may interact with a user. A waypoint specifies where the robot is to move to with respect to the user while a proxemic cost map is used to plan the path to the waypoint. User input or preferences may be used to modify the waypoint or the proxemic cost map. The waypoint may specify a particular distance and bearing with respect to the user. The proxemic cost map may be oriented with respect to the user and specifies costs for particular areas. For example, an area immediately behind the user may have a very high cost while an area in front of the user may have a low cost. Based on the waypoint and the proxemic cost map, a path is selected and the robot moves along that path, avoiding the high cost areas in favor of the low cost areas if possible.

System for dynamic positioning of an autonomous mobile device with respect to a user

A robot uses types of behavior such as approach, follow, avoid, and so forth to move about an environment and interact with a user. An occupancy map provides information about obstacles in the environment. A predicted trajectory of the user is determined that is indicative of expected locations and confidence of those expected locations. The predicted trajectory may be based on the user's movement and the occupancy map. Based on the predicted trajectory and the occupancy map, a target point and a path to the target point is determined. The path may also be based on a proxemic cost map that specifies how regions with respect to the user may be traversed.

Dynamic positioning of an autonomous mobile device with respect to a user trajectory

Growing community of inventors

Sunnyvale, CA, United States of America

Saurabh Gupta