On-line first order backpropagation is sufficiently fast and effective for many large-scale classification problems but for very high precision mappings, batch processing may be the method of choice. This paper reviews first- and second-order optimization methods for learning in feedforward neural networks. The viewpoint is that of optimization: many methods can be cast in the language of optimization techniques, allowing the transfer to neural nets of detailed results about computational complexity and safety procedures to ensure convergence and to avoid numerical problems. The review is not intended to deliver detailed prescriptions for the most appropriate methods in specific applications, but to illustrate the main characteristics of the different methods and their mutual relations.

This paper investigates a tabu search based hyper-heuristic for solving examination timetabling problems. The hyper-heuristic framework uses a tabu list to monitor the performance of a collection of low-level heuristics and then make tabu heuristics that have been applied too many times, thus allowing other heuristics to be applied. Experiments carried out on examination timetabling datasets from the literature show that this approach is able to produce good quality solutions.