Fitness distance correlation of neural network error surfaces: A scalable, continuous optimization problem

This paper investigates neural network training as a potential source of problems for benchmarking continuous, heuristic optimization algorithms. Through the use of a student-teacher learning paradigm, the error surfaces of several neural networks are examined using so-called fitness distance correlation, which has previously been applied to discrete, combinatorial optimization problems. The results suggest that the neural network training tasks offer a number of desirable properties for algorithm benchmarking, including the ability to scale-up to provide challenging problems in high-dimensional spaces