System and method for performing operations on multi-dimensional functions
AssigneeThe Governing Council of the University of Toronto
InventorsTrefor W. Evans, Prasanth B. Nair
Life of this patent
Estimating the term…
Abstract
A system and method for performing operations on multi-dimensional functions using a machine learning model, the method including: receiving a problem formulation in input space; mapping the problem formulation from input space to one or more latent vectors or a set in latent feature space using a projection learned using the machine learning model; splitting the one or more latent vectors or set in latent space into a plurality of lower-dimensional groupings of latent features; performing one or more operations in latent space on each lower-dimensional groupings of latent features; combining each of the low-dimensional groupings; and outputting the combination for generating the prediction.
Claims20
A computer-implemented method for performing operations on multi-dimensional functions using a machine learning model, the method comprising:
- receiving a problem formulation in input space;
- mapping the problem formulation from input space to one or more latent vectors or a set in latent feature space using a projection learned using the machine learning model;
- splitting the one or more latent vectors or set in latent space into a plurality of lower-dimensional groupings of latent features;
- performing one or more operations in latent space on each lower-dimensional groupings of latent features;
- combining each of the low-dimensional groupings;
- and
- outputting the combination for generating the prediction.
A system for performing operations on multi-dimensional functions using a machine learning model, the system comprising one or more processors in communication with a data storage, the one or more processors configured to execute:
- an input module to receive a problem formulation in input space;
- a conversion module to map the problem formulation from input space to one or more latent vectors or a set in latent feature space using a projection learned using the machine learning model, and to split the one or more latent vectors or set in latent space into a plurality of lower-dimensional groupings of latent features;
- an operations module to perform one or more operations in latent space on each lower-dimensional groupings of latent features;
- and
- an output module to combine each of the low-dimensional groupings and to output the combination for generating the prediction.
Dependencies are inferred from the claim text.