Reinforcement testing of a neural network
AssigneeInternational Business Machines Corporation
InventorsANDREW C.M. HICKS, DEBORAH A. FURMAN
Life of this patent
Estimating the term…
Abstract
Aspects of the invention include creating a neural network including neurons to which actions are assigned in representation of test cases. Tests of various instantiations of the neural network are executed for each test case and a state of the neural network after each test is evaluated to determine a fitness score of a corresponding instantiation. Instantiations having fitness scores that exceed a predefined level and identified and the instantiations having the fitness scores that exceed the predefined level are selected for adjustments. The executing, the evaluating, the identifying and the selecting are iteratively repeated in order to obtain desired fitness scores.
Claims20
A computer-implemented method of reinforcement testing of a neural network, the computer-implemented method comprising:
- creating the neural network, the neural network comprising neurons to which actions are assigned in representation of test cases;
- executing tests of various instantiations of the neural network for each test case;
- evaluating a state of the neural network after each test to determine a fitness score of a corresponding instantiation;
- identifying instantiations having fitness scores that exceed a predefined level;
- selecting the instantiations having the fitness scores that exceed the predefined level for adjustments;
- and
- iteratively repeating the executing, the evaluating, the identifying and the selecting in order to obtain desired fitness scores.
A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform operations comprising:
- creating the neural network, the neural network comprising neurons to which actions are assigned in representation of test cases;
- executing tests of various instantiations of the neural network for each test case;
- evaluating a state of the neural network after each test to determine a fitness score of a corresponding instantiation;
- identifying instantiations having fitness scores that exceed a predefined level;
- selecting the instantiations having the fitness scores that exceed the predefined level for adjustments;
- and
- iteratively repeating the executing, the evaluating, the identifying and the selecting in order to obtain desired fitness scores.
A system comprising:
- a memory having computer readable instructions;
- and
- one or more processors for executing the computer readable instructions, the computer readable instructions controlling the one or more processors to perform operations comprising:
- creating a neural network, the neural network comprising neurons to which actions are assigned in representation of test cases;
- executing tests of various instantiations of the neural network for each test case;
- evaluating a state of the neural network after each test to determine a fitness score of a corresponding instantiation;
- identifying instantiations having fitness scores that exceed a predefined level;
- selecting the instantiations having the fitness scores that exceed the predefined level for adjustments;
- and
- iteratively repeating the executing, the evaluating, the identifying and the selecting in order to obtain desired fitness scores.
Dependencies are inferred from the claim text.