Movidius Limited

Sgs-thomson Microelectronics S.r.l.

Linear Algebra Technologies Limited

Intel Corporation

Stmicroelectronics S.r.l.

David Macdara Moloney

Brendan Barry

Fergal Connor

Richard Richmond

Jonathan Byrne

Maurizio Zuffada

Giorgio Betti

Paolo Gadducci

Cormac Brick

Alireza Dehghani

Gianfranco Vai

Fabrizio Sacchi

Xiaofan Xu

Sam Caulfield

Roberto Alini

David Donohoe

Sean Power

Gary Garfield Barrington Baugh

Martin O'Riordan

Ovidiu Andrei Vesa

Valerio Pisati

Anton Shmatov

Alessandro Palla

Kevin Lee

Marco Pio Demicheli

Salvatore Portaluri

Silvano Gornati

Mi Sun Park

Francesco Brianti

Marco Gregori

Léonie Raideen Buckley

Carlos Marquez Rodriguez-Peral

Luca Sarti

Luis Manuel Rodríguez Martin De La Sierra

Carlos Márquez Rodríguez-Peral

Luis M Rodríguez Martín De La Sierra

Dexmont Alejandro Peña Carillo

Ananya Gupta

Dexmont Alejandro Carillo Peña

Tomaso F L Cetto

Yuri Ivanov

Leonie Buckley

Jonathan David Birne

Jonathan David Byrne

A grammar is used in a grammatical evolution of a set of parent neural network models to generate a set of child neural network models. A generation of neural network models is tested based on a set of test data, where the generation includes the set of child neural network models. Respective values for each one of a plurality of attributes are determined for each neural network in the generation, where one of the attributes includes a validation accuracy value determined from the test. Multi-objective optimization is performed based on the values of the plurality of attributes for the generation of neural networks and a subset of the generation of neural network models is selected based on the results of the multi-objective optimization.

Automated generation of neural networks

A view of geometry captured in image data generated by an imaging sensor is compared with a description of the geometry in a volumetric data structure. The volumetric data structure describes the volume at a plurality of levels of detail and includes entries describing voxels defining subvolumes of the volume at multiple levels of detail. The volumetric data structure includes a first entry to describe voxels at a lowest one of the levels of detail and further includes a number of second entries to describe voxels at a higher, second level of detail, the voxels at the second level of detail representing subvolumes of the voxels at the first level of detail. Each of these entries include bits to indicate whether a corresponding one of the voxels is at least partially occupied with the geometry. One or more of these entries are used in the comparison with the image data.

Path planning using sparse volumetric data

Systems and methods for distributed training of deep learning models are disclosed. An example local device to train deep learning models includes a reference generator to label input data received at the local device to generate training data, a trainer to train a local deep learning model and to transmit the local deep learning model to a server that is to receive a plurality of local deep learning models from a plurality of local devices, the server to determine a set of weights for a global deep learning model, and an updater to update the local deep learning model based on the set of weights received from the server.

Systems and methods for distributed training of deep learning models

Example methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to implement video surveillance with neural networks are disclosed. Example systems disclosed herein include a database to store records of operator-labeled video segments (e.g., as records of operator-labeled video segments). The operator-labeled video segments include reference video segments and corresponding reference event labels describing the video segments. Disclosed example systems also include a neural network including a first instance of an inference engine, and a training engine to train the first instance of the inference engine based on a training set of the operator-labeled video segments obtained from the database, the first instance of the inference engine to infer events from the operator-labeled video segments included in the training set. Disclosed example systems further include a second instance of the inference engine to infer events from monitored video feeds, the second instance of the inference engine being based on the first instance of the inference engine.

Video surveillance with neural networks

A raycaster performs a raycasting algorithm, where the raycasting algorithm takes, as an input, a sparse hierarchical volumetric data structure. Performing the raycasting algorithm includes casting a plurality of rays from a reference point into the 3D volume, and, for each of the plurality of rays, traversing the ray to determine whether voxels in the set of voxels are intersected by the ray and are occupied, where the ray is to be traversed according to an approximate traversal algorithm.

Computer vision system

An output of a first one of a plurality of layers within a neural network is identified. A bitmap is determined from the output, the bitmap including a binary matrix. A particular subset of operations for a second one of the plurality of layers is determined to be skipped based on the bitmap. Operations are performed for the second layer other than the particular subset of operations, while the particular subset of operations are skipped.

Dynamic culling of matrix operations

Methods, apparatus, systems and articles of manufacture to reconstruct scenes using convolutional neural networks are disclosed. An example apparatus includes a sensor data acquirer to acquire ground truth data representing an environment, an environment detector to identify an environmental characteristic of the environment, a synthetic database builder to apply noise to the ground truth data to form a training set, a model builder to train a machine learning model using the training set and the ground truth data, and a model adjustor to modify the machine learning model to include residual OR-gate connections intermediate respective layers of the machine learning model. The synthetic database builder is further to store the machine learning model in association with the environmental characteristic of the environment.

Methods, systems, articles of manufacture and apparatus to reconstruct scenes using convolutional neural networks

A volumetric data structure models a particular volume representing the particular volume at a plurality of levels of detail. A first entry in the volumetric data structure includes a first set of bits representing voxels at a first level of detail, the first level of detail includes the lowest level of detail in the volumetric data structure, values of the first set of bits indicate whether a corresponding one of the voxels is at least partially occupied by respective geometry, where the volumetric data structure further includes a number of second entries representing voxels at a second level of detail higher than the first level of detail, the voxels at the second level of detail represent subvolumes of volumes represented by voxels at the first level of detail, and the number of second entries corresponds to a number of bits in the first set of bits with values indicating that a corresponding voxel volume is occupied.

Operations using sparse volumetric data

A machine learning system is provided to enhance various aspects of machine learning models. In some aspects, a substantially photorealistic three-dimensional (3D) graphical model of an object is accessed and a set of training images of the 3D graphical mode are generated, the set of training images generated to add imperfections and degrade photorealistic quality of the training images. The set of training images are provided as training data to train an artificial neural network.

Deep learning system

Methods, systems, articles of manufacture and apparatus to generate digital scenes are disclosed. An example apparatus to generate labelled models includes a map builder to generate a three-dimensional (3D) model of an input image, a grouping classifier to identify a first zone of the 3D model corresponding to a first type of grouping classification, a human model builder to generate a quantity of placeholder human models corresponding to the first zone, a coordinate engine to assign the quantity of placeholder human models to respective coordinate locations of the first zone, the respective coordinate locations assigned based on the first type of grouping classification, a model characteristics modifier to assign characteristics associated with an aspect type to respective ones of the quantity of placeholder human models, and an annotation manager to associate the assigned characteristics as label data for respective ones of the quantity of placeholder human models.

Methods, systems, articles of manufacture and apparatus to generate digital scenes

An example stationary tracker includes memory to store fixed geographic location information indicative of a fixed geographic location of the stationary tracker, and to store a reference feature image; and at least one processor to: determine a feature in an image is a non-displayable feature by comparing the feature to the reference feature image; and generate a masked image, the masked image to mask the non-displayable feature based on the non-displayable feature not allowed to be displayed when captured from the fixed geographic location of the stationary tracker, and the masked image to display a displayable feature in the image; and a wireless interface to detect a wireless tag located on a tag bearer, the at least one processor to determine the tag bearer is the displayable feature in the image based on the wireless tag.

Methods and apparatus to generate masked images based on selective privacy and/or location tracking

The present application discloses a computing device that can provide a low-power, highly capable computing platform for computational imaging. The computing device can include one or more processing units, for example one or more vector processors and one or more hardware accelerators, an intelligent memory fabric, a peripheral device, and a power management module. The computing device can communicate with external devices, such as one or more image sensors, an accelerometer, a gyroscope, or any other suitable sensor devices.

Apparatus, systems, and methods for low power computational imaging

A ray is cast into a volume described by a volumetric data structure, which describes the volume at a plurality of levels of detail. A first entry in the volumetric data structure includes a first set of bits representing voxels at a lowest one of the plurality of levels of detail, and values of the first set of bits indicate whether a corresponding one of the voxels is at least partially occupied by respective geometry. A set of second entries in the volumetric data structure describe voxels at a second level of detail, which represent subvolumes of the voxels at the first lowest level of detail. The ray is determined to pass through a particular subset of the voxels at the first level of detail and at least a particular one of the particular subset of voxels is determined to be occupied by geometry.

Rendering operations using sparse volumetric data

Growing community of inventors

Dublin, Ireland

David Macdara Moloney