Feature selection and classification using age layered population structure genetic programming
2016 IEEE Congress on Evolutionary Computation (CEC)
The curse of dimensionality is a major problem in the fields of machine learning, data mining and knowledge discovery. Exhaustive search for the most optimal subset of relevant features from a high dimensional dataset is NP hard. Sub-optimal population based stochastic algorithms such as GP and GA are good choices for searching through large search spaces, and are usually more feasible than exhaustive and deterministic search algorithms. On the other hand, population based stochastic algorithms
... often suffer from pre-mature convergence on mediocre sub-optimal solutions. The Age Layered Population Structure (ALPS) is a novel meta-heuristic for overcoming 1. Brian J. Ross for accepting me as a student and providing two years of excellent supervision, guidance, and funding.I could not have gotten a better supervisor. Beatrice Ombuki-Berman and Sheridan Houghten for their participation on the supervisory committee. 3. Cale Fairchild for providing an outstanding technical support and knowledge on computing clusters and Linux expertise. 4. The Computer Science department and Brock Graduate School for providing me with the privilege, facilities, funding and enabling environment to accomplish something great. Love is patient and kind. Love is not jealous. It does not brag, does not get puffed up, does not behave indecently, does not look for its own interests, does not become provoked. It does not keep account of the injury. It does not rejoice over unrighteousness, but rejoices with the truth. It bears all things, belives all things, hopes all things, endures all things. Love never fails.