Neural network based prototyping system and method

• US 5,852,815 A
• Filed: 05/15/1998
• Issued: 12/22/1998
• Est. Priority Date: 01/26/1996
• Status: Expired due to Term

• Current Assignee: Stephen L. Thaler
• Original Assignee: Stephen L. Thaler
• Inventors: Thaler, Stephen L.
• Primary Examiner(s): Davis, George B.
• Application Number:
  US09/079,730
• Time in Patent Office: 221 Days
• Field of Search: 706/16, 706/20, 706/25, 706/39
• US Class Current: 706/16
• CPC Class Codes: G06N 3/047 Probabilistic or stochastic networks
• CPC Class Codes: G06N 3/105 Shells for specifying net layout

Abstract

Constructing and simulating artificial neural networks and components thereof within a spreadsheet environment results in user friendly neural networks which do not require algorithmic based software in order to train or operate. Such neural networks can be easily cascaded to form complex neural networks and neural network systems, including neural networks capable of self-organizing so as to self-train within a spreadsheet, neural networks which train simultaneously within a spreadsheet, and neural networks capable of autonomously moving, monitoring, analyzing, and altering data within a spreadsheet. Neural networks can also be cascaded together in self training neural network form to achieve a device prototyping system.

Claims

1. A neural network based prototyping system for prototyping construction of a device from a plurality of known components, wherein a desired relationship between inputs and outputs of the device being prototyped is known, comprising:

a computer operable to electronically generate a data space including a plurality of cells which are interrelatable through relative cell referencing,

a plurality of component neural networks, each component neural network trained within a knowledge domain of one of the known components so as to emulate a relationship between inputs and outputs to the known component, each component neural network implemented in said data space,

a prototyping neural network implemented in said data space and including at least one hidden layer having a plurality of neurons, at least one hidden layer neuron represented by one of said component neural networks, and an output layer having at least one neuron, each hidden layer neuron and each output layer neuron having at least one numeric weighting value associated therewith for weighting inputs thereto, and

means for adjusting at least some of said numeric weighting values so as to incorporate into said prototyping neural network a knowledge domain represented by the known desired relationship between inputs and outputs of the device being prototyped, so that, after said knowledge domain represented by the known desired relationship between inputs and outputs of the device being prototyped has been incorporated into said prototyping neural network, said numeric weighting values are indicative of how the known components should be interconnected in order to construct the device being prototyped.

2. A neural network based prototyping system in accordance with claim 1 wherein at least one output layer neuron being represented by one of said component neural networks.

3. A neural network based prototyping system in accordance with claim 1 wherein said means for adjusting at least some of said numeric weighting values includes a training network implemented in said data space, said training network operable to determine, for each hidden layer neuron and each output layer neuron, a derivative of an activation level thereof with respect to a net input thereto.

4. A neural network based prototyping system in accordance with claim 3 wherein said training network is further operable to determine a weight update term for each numeric weighting value to be adjusted, and said means for adjusting at least some of said numeric weighting values further includes a program associated with said prototyping neural network and said training network, said program operable to add each weight update term to its corresponding numeric weighting value.

5. A neural network based prototyping system in accordance with claim 3 wherein said training network is further operable to determine a new numeric value for each numeric weighting value to be adjusted, and said means for adjusting at least some of said numeric weighting values further includes a program associated with said prototyping neural network and said training network, said program operable to replace each numeric weighting value which is to be adjusted with its new numeric value.

6. A neural network based prototyping system in accordance with claim 1 wherein said means for adjusting at least some of said numeric weighting values includes a training network implemented in said data space, and means for applying a plurality of sets of training data to said prototyping neural network.

7. A neural network based prototyping system in accordance with claim 6 wherein said plurality of sets of training data are located within said data space and said means for applying a plurality of sets of training data to said prototyping neural network includes a program associated with said prototyping neural network and said training network, said program operable to effect movement said prototyping network within said data space such that with each movement thereof, a set of training data is applied to said prototyping neural network.

8. A method of utilizing neural networks to prototype a configuration of a device which will achieve a predetermined relationship between inputs thereto and outputs therefrom, wherein the device is to be constructed from a plurality of known components, each component simulated by a component neural network within a spreadsheet of a spreadsheet application, the component neural networks associated within the spreadsheet to form a prototyping neural network including a plurality of neurons, each neuron including at least one input, each input having an associated weight, wherein at least some of the neurons of the prototyping neural network are represented by one of the component neural networks, said method comprising the steps of:

(a) assigning a value to the weight associated with each input,

(b) performing a training operation, said training operation comprising the steps of;

(i) applying a training input to the prototyping neural network,

(ii) determining within the spreadsheet, for each weight, a weight update term,

(iii) adjusting each weight to reflect the determined weight update term,

(iv) determining an error indicative of the training status of the prototyping neural network by comparing a desired training output to an actual output of the prototyping neural network,

(c) repeating steps b(i) through b(iv) until said error falls below a predetermined value, and

(d) correlating the weights of the prototyping neural network to how the known components should be interconnected to construct the device.

9. A method of utilizing neural networks to prototype a configuration of a device which will achieve a predetermined relationship between inputs thereto and outputs therefrom in accordance with claim 8, the predetermined relationship between inputs thereto and outputs therefrom represented by a plurality of known inputs and associated desired outputs, wherein step (b)(i) includes the prototyping neural network relatively referencing said training input.

10. A method of utilizing neural networks to prototype a configuration of a device which will achieve a predetermined relationship between inputs thereto and outputs therefrom in accordance with claim 8 wherein step (a) includes assigning a random value to the weight associated with each input.

11. A method of utilizing neural networks to prototype a configuration of a device which will achieve a predetermined relationship between inputs thereto and outputs therefrom in accordance with claim 8 wherein steps (b)(i) through (b)(iv) are performed each time a calculate function associated with the spreadsheet is activated.

12. A method of utilizing neural networks to prototype a configuration of a device which will achieve a predetermined relationship between inputs thereto and outputs therefrom in accordance with claim 8 wherein the repetition of steps (b)(i) through (b)(iv) is achieved by a program associated with the prototyping neural network.

13. A method of utilizing neural networks to prototype a configuration of a device which will achieve a predetermined relationship between inputs thereto and outputs therefrom in accordance with claim 8 wherein step (b)(ii) includes determining, for each neuron of the plurality of neurons, a derivative of activation level thereof with respect to net input thereto.