Cardinal sine as an activation function for universal classifier training data
AssigneeInternational Business Machines Corporation
InventorAbhishek Dasgupta
Life of this patent
Estimating the term…
Abstract
Cardinal sine function used as an activation function for a hierarchical classifier. Application of a sine function, or a cardinal sine function, for hierarchical classification of a subject within subject matter domains and sub-domains. Hierarchical classification or multi-level classification is improved through use of the cardinal sine function or even standard sine function. Some embodiments of the present invention focus on the usage of cardinal sine function as activation function and how to apply this cardinal sine function for hierarchical classification of a subject. Some embodiments include a technique by which hierarchical classification or multi-level classification can benefit from application of a cardinal sine function.
Claims18
A computer-implemented method comprising:
- receiving an untrained hierarchical classifier than includes an artificial neural network that includes a directed graph model including a plurality of nodes and a plurality of directed connections among and between the nodes;
- and
- training the untrained hierarchical classifier algorithm to obtain a trained hierarchical classifier using a sinc function as an activation function.
A computer program product comprising:
- a machine readable storage device;
- and
- computer code stored on the machine readable storage device, with the computer code including instructions for causing a processor(s) set to perform operations including the following:
- receiving an untrained hierarchical classifier than includes an artificial neural network that includes a directed graph model including a plurality of nodes and a plurality of directed connections among and between the nodes, and
- training the untrained hierarchical classifier algorithm to obtain a trained hierarchical classifier using a sinc function as an activation function.
A computer system comprising:
- a processor(s) set;
- a machine readable storage device;
- and
- computer code stored on the machine readable storage device, with the computer code including instructions for causing the processor(s) set to perform operations including the following:
- receiving an untrained hierarchical classifier than includes an artificial neural network that includes a directed graph model including a plurality of nodes and a plurality of directed connections among and between the nodes, and
- training the untrained hierarchical classifier algorithm to obtain a trained hierarchical classifier using a sinc function as an activation function.
Dependencies are inferred from the claim text.