Abstract A neural network shell has a defined interface to an application program. By interfacing with the neural network shell, any application program becomes a neural network application program. The neural network shell contains a set of utility programs that transfers data into and out of a neural network data structure. This set of utility programs allows an application program to define a new neural network model, create a neural network data structure, train a neural network, and run a neural network. Once trained, the neural network data structure can be transported to other computer systems or to application programs written in different computing languages running on similar or different computer systems.
A method in a neural network shell of enabling an application program to run one of a plurality of defined neural network models, thereby becoming a neural network having an input for data and an output for a result, said method comprising the machine-executed steps of: creating a neural network data structure having a plurality of parameters and a plurality of data arrays specific to a selected one of said plurality of defined neural network models; teaching said neural network by presenting training data at said input of said neural network and repeatedly adjusting the values of said plurality of data arrays until said result at said output is within tolerance of a correct result; and running said neural network by presenting actual data at said input and retrieving the result from said output of said neural network.
Claim 2
Independent Claim
138 words
A method in a neural network shell of enabling an application program to run one of a plurality of defined neural network models, thereby becoming a neural network having an input for data and an output for a result, said method comprising the machine-executed steps of: creating a neural network data structure having a plurality of parameters and a plurality of data arrays specific to a selected one of said plurality of defined neural network models; teaching said neural network by presenting training data at said input of said neural network and repeatedly adjusting the values of said plurality of data arrays until said result at said output is within tolerance of a correct result; and running said neural network by presenting actual data at said input and retrieving the result from said output of said neural network.