1. Coevolutionary Automated Software Correction
Josh Wilkerson
PhD Candidate in Computer Science
Missouri S&T

2. Technical Background Evolutionary Algorithms (EAs)
Subfield of evolutionary computation (in artificial intelligence)
Based on biological evolution
Uses mutation, reproduction, and selection
Population composed of candidate solutions
Needed:
Solution representation
Fitness function
Applicable to a wide variety of fields
Makes no assumptions about the problem space (ideally)

3. Technical Background EA Operation Start with an initial population
Each generation
Create new individuals and evaluate them
Population competition (survival of the fittest)
Mutation and reproduction
Explore the problem space
Bring in new genetic material
Selection
Applies pressure to individuals
More fit individuals are selected for mutation and reproduction more often 3

4. Technical Background Genetic Programming Coevolution Type of EA
Evolves tree representations
E.g., computer program parse trees
Coevolution
Extension of standard EA
Fitness dependency between individuals
Dependency can be either cooperative or competitive
CASC system uses competitive coevolution
Evolutionary arms-race 4

5. High Level View of CASC
View the problem space as all possible software artifacts
Use the given software artifact as a starting point
Use the correct version(s) of the given software artifact as the goal point
Generate test cases to guide the evolution of the software artifact
Evolve the software artifacts in order to handle the test cases better (and ultimately perform better)
Evolve the test cases in order to better find flaws in the software artifacts
Competitive coevolutionary arms race results

6. CASC Evolutionary Model

7. CASC Evolutionary Model

8. CASC Evolutionary Model
Evaluate all individuals, assign fitness
Discuss the details of evaluation later

9. CASC Evolutionary Model

10. Reproduction Phase: Programs
Randomly select a genetic operation to perform
Probability of operation selection is configurable
Perform operation, generate new program(s)
Add new individuals to population
Repeat until specified number of individuals has been created 10

11. Reproduction Phase: Programs
Genetic Operations
Reset
Copy
Crossover
Two individuals are randomly selected based off fitness
Randomly select and exchange compatible sub-trees
Generates two new programs
Mutation
Randomly select individual based off fitness
Randomly select and change mutable node
Generate a new sub-tree (if necessary)
Architecture Altering Operations
Reselection is allowed for all operators
Only specific nodes are considered for mutation (critical points)
Numeric constants and unmodified variables
Identified dynamically

12. Reproduction Phase: Test Cases
Reproduction employs uniform crossover
Each offspring has a chance to mutate
Genes to mutate are selected random
Mutated gene is randomly adjusted
The amount adjusted is selected from a Gaussian distribution
Only specific nodes are considered for mutation (critical points)
Numeric constants and unmodified variables
Identified dynamically 12

13. CASC Evolutionary Model13

14. CASC Evolutionary Model

15. CASC Evolutionary Model
Trim populations back down to specified size
Reverse tournament selection

16. CASC Evolutionary Model
e.g. Number of generations, goal fitness reached, population converged on maxima (low diversity), etc.

17. CASC Implementation Details
Adaptive parameter control
EAs typically have many control parameters
Difficult to find optimal settings for these parameters
In CASC genetic operator probabilities are adaptive parameters
Rewarded/punished based on performance
If one operator is generating improved individuals more than the others make it more likely to be used
Allows the system to adapt to the different phases in the search

18. CASC Implementation Details
Parallel Computation
Computational complexity is generally a problem for Eas
CASC writes, compiles, and executes hundreds (or even thousands) of C++ programs in a given run
To reduce run times this is done in parallel (on the NIC cluster here on campus)
Main node: responsible for generating and writing programs
Worker nodes: responsible for compiling and executing programs
Dramatically speeds up execution
Investigating new options for this (discussed later) 18

19. Current and Future Work
Fitness Function Design
For each new problem CASC needs a new fitness function
Fitness function design can often be difficult
Developing a guide for fitness function design
Starts a program specifications
Walks through the thought process for designing a fitness function for the problem
Long term goal: automate fitness function creation 19

20. Current and Future Work
File system slow down
CASC is writing and compiling many many programs each run
I.e., many many files in the file system each run
File system access is bottlenecking the speed of the CASC system
Currently reworking the system to store program files and executables in RAM
Uses a virtually mounted hard disk that stored data in RAM
Expecting a dramatic speed up (fingers crossed…)
Other option: distributed computing (like BOINC, etc.) 20

21. Current and Future Work
Scalability
As program size increases so does the problem space
Many more modifications possible
More genetic material
Investigating options to allow CASC to scale with problem size
Current idea: break the program up into pieces
Multiple program populations
Each population is based on a piece of the original program
Each population has its own objective
Cooperative coevolution 21

22. Current and Future Work
Add new diagram 22

23. Questions?