Apple Inc.

Applied Brain Research Inc.

Seiko Epson Corporation

Yichuan Tang

Ruslan Salakhutdinov

Nitish Srivastava

Christopher David Eliasmith

Hanlin Goh

Terrence Charles Stewart

Travis Crncich-DeWolf

Trevor William Bekolay

Daniel Halden Rasmussen

Feng-Xuan Choo

Hui Zhou

Rui Hu

Daniel Haiden Rasmussen

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

At a centralized model trainer, one or more neural network based models are trained using an input data set. At least a first set of parameters of a model is transmitted to a model deployment destination. Using a second input data set, one or more adaptive parameters for the model are determined at the model deployment destination. Using the adaptive parameters, one or more inferences are generated at the model deployment destination.

Adaptive training of neural network models at model deployment destinations

Sensor data captured by one or more sensors may be received at an analysis system. A neural network may be used to detect an object in the sensor data. A plurality of polygons surrounding the object may be generated in one or more subsets of the sensor data. A prediction of a future position of the object may be generated based at least in part on the polygons. One or more commands may be provided to a control system based on the prediction of the future position.

Analysis of objects of interest in sensor data using deep 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, 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.

A system includes a state-dependent action policy and a state-dependent transition policy. The state-dependent action policy determines an action based on environment states and a current agent state selected from a predetermined group of agent states. The state-dependent transition policy is implemented using one or more machine learning models and is configured to control transitions between agent states from the predetermined group of agent states.

Neural finite state machines

Methods, systems and apparatus that provide for perceptual, cognitive, and motor behaviors in an integrated system implemented using neural architectures. Components of the system communicate using artificial neurons that implement neural networks. The connections between these networks form representations&#x2014;referred to as semantic pointers&#x2014;which model the various firing patterns of biological neural network connections. Semantic pointers can be thought of as elements of a neural vector space, and can implement a form of abstraction level filtering or compression, in which high-dimensional structures can be abstracted one or more times thereby reducing the number of dimensions needed to represent a particular structure.

Methods and systems for artificial cognition

A system employs an inspection neural network (INN) to inspect data generated during an inference process of a primary neural network (PNN) to generate an indication of reliability for an output generated by the PNN. The system includes a sensor configured to capture sensor data. Sensor data captured by the sensor is provided to a data analyzer to generate an output using the PNN. An analyzer inspector is configured to capture inspection data associated with the generation of the output by the data analyzer, and use the INN to generate an indication of reliability for the PNN's output based on the inspection data. The INN is trained using a set of training data that is distinct from the training data used to train the PNN.

Inspection neural network for assessing neural network reliability

A method of identifying regions of different content in an image comprises dividing image data into a plurality of pixel blocks, extracting features of the pixel blocks and classifying the content of the pixel blocks based on extracted features. Extracting comprises, for each pixel block, convolving a magic square filter with the pixels of the pixel block and summing the results, and calculating the percentage of background pixels in the pixel block. The magic square filter is a 3&#xd7;3 kernel that has a specific selectivity towards the statistical appearance and geometric alignment of a document based text of various fonts, sizes and styles. The complete sum of the magic square filter, as well as the sum of the rows, columns and diagonals of the magic square filter are zero.

Growing community of inventors

Mississauga, Canada

Yichuan Tang