Content deleted Content added
m Signing comment by Gost80 - "→Questioning the no assumption statement: new section" |
|||
Line 41:
The core bias in evolutionary computation is the binary search space which is typical. Without this bias, the search space will simply be a set of numbers with no relationships between them. The binary search space introduces the bias of correlation between fitness and hamming distance, whether true or not. This is why problems for which this is true such as Gen 1-MAX are easy with O(n log n) for EAs (http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.5599). Another way of saying this is that the fact that you talk about a fitness landscape at all is a bias. If you truly had no bias, there would not be any landscape to speak of. It would just be a S -> R map. <small><span class="autosigned">— Preceding [[Wikipedia:Signatures|unsigned]] comment added by [[User:Gost80|Gost80]] ([[User talk:Gost80|talk]] • [[Special:Contributions/Gost80|contribs]]) 17:33, 11 September 2011 (UTC)</span></small><!-- Template:Unsigned --> <!--Autosigned by SineBot-->
Moreover, the primary reason EC has enjoyed a lot of success is not just because its base bias is nothing more than a multi-dimensional search space. It is also because it acts as a framework for inserting a large number of biases though custom selection operators and custom mutation operators and representations. Its relative lack of primary bias reduces interference with custom biases allowing it to specialise in a wider variety of fields. But this happens only with the effort of scientists who build in custom biases into the EA though operators and such.
| |||