Explorations in parallel distributed processing: a handbook of models, programs, and exercises
Explorations in parallel distributed processing: a handbook of models, programs, and exercises
Biological Cybernetics
Genetic programming: on the programming of computers by means of natural selection
Genetic programming: on the programming of computers by means of natural selection
Synthesis of neural networks using a two-dimensional approach
Evolution of engineering and information systems and their applications
Foundations of genetic programming
Foundations of genetic programming
Evolving the Topology and the Weights of Neural Networks Using a Dual Representation
Applied Intelligence
On classes of functions for which No Free Lunch results hold
Information Processing Letters
Focused no free lunch theorems
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Free lunches for function and program induction
Proceedings of the tenth ACM SIGEVO workshop on Foundations of genetic algorithms
A comparison between cellular encoding and direct encoding for genetic neural networks
GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
Two broad classes of functions for which a no free lunch result does not hold
GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartII
No free lunch, program induction and combinatorial problems
EuroGP'03 Proceedings of the 6th European conference on Genetic programming
A Field Guide to Genetic Programming
A Field Guide to Genetic Programming
WILF'05 Proceedings of the 6th international conference on Fuzzy Logic and Applications
No free lunch theorems for optimization
IEEE Transactions on Evolutionary Computation
| Hi-index | 0.00 |
In this paper we prove that for a variety of practical situations, the no-free-lunch (NFL) theorem does not apply to algorithms that search the space of artificial neural networks, such as evolutionary algorithms. We find, in particular, that, while conditions under which NFL applies exist, these require extremely restrictive symmetries on the set of possible problems which are unlikely encountered in practice. In other words, not all algorithms are equally good at finding neural networks that solve problems under all possible performance measures: a superior search algorithm for this domain does exist.