Prosiectau fesul blwyddyn
Crynodeb
The classical Geiringer theorem addresses the limiting frequency of occurrence of various alleles after repeated application of crossover. It has been adopted to the setting of evolutionary algorithms and, a lot more recently, reinforcement learning and MonteCarlo tree search methodology to cope with a rather challenging question of action evaluation at the chance nodes. The theorem motivates novel dynamic parallel algorithms that are explicitly described in the current paper for the first time. The algorithms involve independent agents traversing a dynamically constructed directed graph that possibly has loops and multiple edges. A rather elegant and profound categorytheoretic model of cognition in biological neural networks developed by a wellknown French mathematician, professor Andree Ehresmann jointly with a neurosurgeon, Jan Paul Vanbremeersch over the last thirty years provides a hint at the connection between such algorithms and Hebbian learning.
Iaith wreiddiol  Saesneg 

Tudalennau (oi)  473484 
Cyfnodolyn  Natural Computing 
Cyfrol  12 
Rhif cyhoeddi  4 
Dynodwyr Gwrthrych Digidol (DOIs)  
Statws  Cyhoeddwyd  01 Rhag 2013 
Ôl bys
Gweld gwybodaeth am bynciau ymchwil 'Geiringer theorems: from population genetics to computational intelligence, memory evolutive systems and Hebbian learning'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.Prosiectau
 1 Wedi Gorffen

Evolutionary Approximation Algorithms for Optimization: Algorithm design and Complexity Analysis
He, J. (Prif Ymchwilydd)
Engineering & Physical Sciences Research Council
01 Mai 2011 → 31 Hyd 2015
Prosiect: Ymchwil a ariannwyd yn allanol