Grad neural networks for unstructured data
AssigneeInternational Business Machines Corporation
InventorsLior Horesh, Raya Horesh, Elliot Holtham
Life of this patent
Estimating the term…
Abstract
An illustrative embodiment includes a method for analyzing unstructured multidimensional data with a neural network. The method includes designing the neural network at least in part by defining differential operators conforming with dimensions of the data. The method also includes performing forward propagation at a given convolution layer of the neural network at least in part by: obtaining one or more convolved values at least in part by performing convolution over an object within the data, processing respective convolved values to obtain output, and updating the object based at least in part on the output.
Claims20
A method for analyzing unstructured multidimensional data with a neural network, the method comprising:
- designing the neural network at least in part by defining differential operators conforming with dimensions of the data;
- and
- performing forward propagation at a given convolution layer of the neural network at least in part by:
- obtaining one or more convolved values at least in part by performing convolution over an object within the data;
- processing respective convolved values to obtain output;
- and
- updating the object based at least in part on the output.
An apparatus for analyzing unstructured multidimensional data with a neural network, the method comprising:
- a memory;
- and
- at least one processor coupled to the memory, the processor being operative:
- to design the neural network at least in part by defining differential operators conforming with dimensions of the data;
- and
- to perform forward propagation at a given convolution layer of the neural network at least in part by:
- obtaining one or more convolved values at least in part by performing convolution over an object within the data;
- processing respective convolved values to obtain output;
- and
- updating the object based at least in part on the output.
A computer program product comprising a non-transitory machine-readable storage medium having machine-readable program code embodied therewith, said machine-readable program code comprising machine-readable program code configured:
- to design a neural network at least in part by defining differential operators conforming with dimensions of a set of unstructured multidimensional data;
- and
- to perform forward propagation at a given convolution layer of the neural network at least in part by:
- obtaining one or more convolved values at least in part by performing convolution over an object within the set of data;
- processing respective convolved values to obtain output;
- and
- updating the object based at least in part on the output.
Dependencies are inferred from the claim text.