Multi-module genetic programming with multiple genetic data representations
View Patent ↗A method for genetic programming which is based on multiple genetic data component representations. Multiple genetic data component representations are determined and a solution is evolved using a set of genetic data components represented by the multiple genetic data component representations.
1. A method for genetic programming, comprising the steps of:
determining a first genetic data component representation for expressing a solution model;
determining a second genetic data component representation for expressing the solution model;
generating a candidate solution by combining a genetic data component having the first genetic data component representation from a first parent solution with a genetic data component having the first genetic data component representation from a second parent solution and combining a genetic data component having the second genetic data component representation from the first parent solution with a genetic data component having the second genetic data component representation from the second parent solution; and
realizing the solution model as a recipe for constructing a structure that includes a neural network or an electrical circuit.
2. The method of claim 1 , wherein the first and second genetic data component representations pertain to a first and a second module, respectively, of the solution model.
3. The method of claim 2 , wherein the first and second modules include a program module.
4. The method of claim 3 , wherein the genetic data component representation for the program module is a parse tree.
5. The method of claim 3 , wherein the genetic data component representation for the program module is a sequence of instructions.
6. The method of claim 2 , wherein the first and second modules include a parameters module.
7. The method of claim 6 , wherein the genetic data component representation for the parameters module is a sequence of numbers.
8. The method of claim 7 , wherein the sequence of numbers provides a set of parameters for a program module.
9. The method of claim 7 , wherein the sequence of numbers provides a set of parameters for a math function module.
10. The method of claim 7 , wherein the sequence of numbers provides a set of weights for a neural network module.
11. The method of claim 2 , wherein the first and second modules include a neural network module.
12. The method of claim 11 , wherein a the genetic data component representation of the neural network module is a parse tree.
13. The method of claim 2 , wherein the first and second modules include a math function module.
14. The method of claim 13 , wherein a the genetic data component representation of the math function module is a parse tree.
15. The method of claim 1 , wherein the steps of combining include the step of matching the first and second genetic data component representations.