Methods and apparatus for training a matrix-based differentiable program using a photonics-based processor. The matrix-based differentiable program includes at least one matrix-valued variable associated with a matrix of values in a Euclidean vector space. The method comprises configuring components of the photonics-based processor to represent the matrix of values as an angular representation, processing, using the components of the photonics-based processor, training data to compute an error vector, determining in parallel, at least some gradients of parameters of the angular representation, wherein the determining is based on the error vector and a current input training vector, and updating the matrix of values by updating the angular representation based on the determined gradients.

A computer-implemented method for inferring a 3D structure of a genome is provided. The method includes providing genome interaction data and operating an autoencoder including a structured sequence of n autoencoder units, each of which including an encoder unit and a decoder unit, each of which is implemented as a recurrent neural network unit. The method includes additionally training the autoencoder by feeding all vectors of genome interaction data to the encoder units. Thereby, the training of the auto-encoder units is performed stepwise by using inner state of respective previous autoencoder units in the cascaded sequence of autoencoder units and performing backpropagation within each of the plurality of autoencoder units after all autoencoder units have processed their respective input values, and using the output values of the encoder units for deriving a 3D model for a visualization of the genome.

An optical computing device includes: a light-diffraction element group including planar light-diffraction elements made of a photo-curable resin; and a tubular body that houses the light-diffraction element group and that has an inner surface to which at least a part of a perimeter of each of the planar light-diffraction elements is fixed.

An optical computing device includes: a light-diffraction element group including planar light-diffraction elements made of a photo-curable resin; and a tubular body that houses the light-diffraction element group and that has an inner surface to which at least a part of a perimeter of each of the planar light-diffraction elements is fixed.

Disclosed herein are systems, methods, software, and platforms for generating and associating an identifier for an individual. Also disclosed herein are systems, methods, software, and platforms for generating personalized and customized suggestions for caring and treating the individual based on the identifier of the individual.

A pet medical text recognizer may include one or more machine learning classifiers. The one or more machine learning classifiers may be trained using training data to associate raw text with pet clinical event codes. A performance metric may be provided, and the highest performing classifier according to the performance metric may be selected as the model for the pet medical text recognizer. The pet medical text recognizer may accept input text from a veterinary practice management system and generate a pet clinical event code for the text. A set of codes associated with a single pet may be aggregated into a pet health record.

An expanded Bell state generator can generate a Bell state on four output modes of a set of m output modes, where m is greater than four. Some expanded Bell state generators can receive inputs on any four of a set of 2m input modes. Subsets of the m output modes can be multiplexed to reduce the number of modes to four. According to some embodiments, a set of 2×2 muxes can be used to rearrange the output modes prior to reducing the number of modes.

Embodiments of the invention relates to a data processing apparatus comprising a processor configured to provide a neural network, wherein the neural network comprises a neural network layer being configured to generate from an array of input data values an array of output data values based on a plurality of position dependent kernels and a plurality of input data values of the array of input data values. Moreover, embodiments of the invention relates to a corresponding data processing method.

A processor-implemented method of performing a convolution operation is provided. The method includes obtaining input feature map data and kernel data, determine the kernel data based on a number of input channels of the input feature map, a number of output channels of an output feature map, and a number of groups of the input feature map data and a number of groups of the kernel data related to the convolution operation, and performing the convolution operation based on the input feature map data and the determined kernel data.

Methods and apparatus for training a matrix-based differentiable program using a photonics-based processor. The matrix-based differentiable program includes at least one matrix-valued variable associated with a matrix of values in a Euclidean vector space. The method comprises configuring components of the photonics-based processor to represent the matrix of values as an angular representation, processing, using the components of the photonics-based processor, training data to compute an error vector, determining in parallel, at least some gradients of parameters of the angular representation, wherein the determining is based on the error vector and a current input training vector, and updating the matrix of values by updating the angular representation based on the determined gradients.