Google Inc.

Waymo LLC

Dependable Ai, Inc.

Vijay Vasudevan

Quoc V Le

Barret Zoph

Jonathon Shlens

Jiquan Ngiam

Pei Sun

Benjamin James Caine

Jeffrey Adgate Dean

Sanjay Ghemawat

Dragomir Dimitrov Anguelov

Ruoming Pang

Zhifeng Chen

Bo Chen

Yin Zhou

Ouais Alsharif

Mingxing Tan

Ekin Dogus Cubuk

Wei Han

Brandon Chauloon Yang

Yu Ouyang

Yu Zhang

Chen Wu

Junhua Mao

Paul Ronald Barham

Jiyang Gao

Yuning Chai

Zijian Guo

Zhengdong Zhang

Christoph Sprunk

Irwan Bello

Xiao Meng Zhang

Patrick An Phu Nguyen

Marc Rasi

Weiyue Wang

Jaran Charumilind

Xi Yi

Bo Zhi See

Joshua Newman

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining update rules for training neural networks. One of the methods includes generating, using a controller neural network, a batch of output sequences, each output sequence in the batch defining a respective update rule; for each output sequence in the batch: training a respective instance of a child neural network using the update rule defined by the output sequence; evaluating a performance of the trained instance of the child neural network on the particular neural network task to determine a performance metric for the trained instance of the child neural network on the particular neural network task; and using the performance metrics for the trained instances of the child neural network to adjust the current values of the controller parameters of the controller neural network.

Neural network optimizer search

Techniques are presented for managing access to external resources while executing code. The method involves receiving a request to execute code and sending an identifier (ID) for the code execution and credentials for accessing an external resource to a trusted server. The request is sent to execute the code with the ID to a code executer, and the code is executed. During code execution, an operation for accessing the external resource is detected. In response to the detection, a request to access the external resource is sent from the code executer to the trusted server. The trusted server accesses the external resource using the provided credentials and sends a response with the results back to the code executer. The code executer does not have access to the credentials for accessing the external resource. After the code terminates execution, the results from the code execution are presented on a device.

Protection of user credentials during code execution

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network having controller parameters and in accordance with current values of the controller parameters, a batch of output sequences. The method includes, for each output sequence in the batch: generating an instance of a child convolutional neural network (CNN) that includes multiple instances of a first convolutional cell having an architecture defined by the output sequence; training the instance of the child CNN to perform an image processing task; and evaluating a performance of the trained instance of the child CNN on the task to determine a performance metric for the trained instance of the child CNN; and using the performance metrics for the trained instances of the child CNN to adjust current values of the controller parameters of the controller neural network.

Neural architecture search for convolutional neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning a data augmentation policy for training a machine learning model. In one aspect, a method includes: receiving training data for training a machine learning model to perform a particular machine learning task; determining multiple data augmentation policies, comprising, at each of multiple time steps: generating a current data augmentation policy based on quality measures of data augmentation policies generated at previous time steps; training a machine learning model on the training data using the current data augmentation policy; and determining a quality measure of the current data augmentation policy using the machine learning model after it has been trained using the current data augmentation policy; and selecting a final data augmentation policy based on the quality measures of the determined data augmentation policies.

Learning data augmentation policies

The present disclosure is directed to an automated neural architecture search approach for designing new neural network architectures such as, for example, resource-constrained mobile CNN models. In particular, the present disclosure provides systems and methods to perform neural architecture search using a novel factorized hierarchical search space that permits layer diversity throughout the network, thereby striking the right balance between flexibility and search space size. The resulting neural architectures are able to be run relatively faster and using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art mobile-optimized models.

Neural architecture search with factorized hierarchical search space

Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for processing a perspective view range image generated from sensor measurements of an environment. The perspective view range image includes a plurality of pixels arranged in a two-dimensional grid and including, for each pixel, (i) features of one or more sensor measurements at a location in the environment corresponding to the pixel and (ii) geometry information comprising range features characterizing a range of the location in the environment corresponding to the pixel relative to the one or more sensors. The system processes the perspective view range image using a first neural network to generate an output feature representation. The first neural network comprises a first perspective point-set aggregation layer comprising a geometry-dependent kernel.

Processing perspective view range images using neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing data generated by a sensing system that rotationally senses an environment. In one aspect, a method comprises partitioning a predetermined period of time into a plurality of sub-periods, wherein the predetermined period of time is a period of time for which data generated by the sensing system constitutes a complete rotational sensing of the environment; for each sub-period: receiving current data generated by the sensing system during the sub-period and characterizing a respective partial scene of the environment; processing the current data using an object detection neural network to generate a current object detection output that is specific to the respective partial scene of the environment.

Streaming object detection within sensor data

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data using dynamic voxelization. When deployed within an on-board system of a vehicle, processing the point cloud data using dynamic voxelization can be used to make autonomous driving decisions for the vehicle with enhanced accuracy, for example by combining representations of point cloud data characterizing a scene from multiple views of the scene.

Processing point clouds using dynamic voxelization

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data representing a sensor measurement of a scene captured by one or more sensors to generate an object detection output that identifies locations of one or more objects in the scene. When deployed within an on-board system of a vehicle, the object detection output that is generated can be used to make autonomous driving decisions for the vehicle with enhanced accuracy.

Object detection in point clouds

Growing community of inventors

Los Altos Hills, CA, United States of America

Vijay Vasudevan