Wyniki wyszukiwania - BazTech

1

Evolving adaptive recurrent networks with Developmental Symbolic Encoding

Suchorzewski M.

Metody Informatyki Stosowanej

|

2010

|

nr 1 (22)

175-187

EN

In this paper we are concerned with evolutionary synthesis of recurrent networks capable of learning in the environment. First, we define the model of network we aim to evolve, which is weightless recurrent network of basic arithmetic nodes. Next, we propose a developmental genetic representation for the network, along with some genetic operators for it. The representation bears some important characteristics such as closure and completeness. Most notably, however, it features modularity and scalability, which we demonstrate on a parity problem. Finally, we evolve the network capable of successful learning in some narrow problem domain. The result shows, that for a given problem domain, evolutionary approach may produce networks performing better than generic neural networks.

2

Evolving weighted topologies for neural networks using genetic programming

Suchorzewski M.

Metody Informatyki Stosowanej

|

2008

|

nr 4 (Tom 17)

211--219

EN

NeuroEvolution of Augmenting Topologies (NEAT) is a method of evolving weighted topologies for neural networks, which has been showed to be effective in solving double pole balancing problems. Its usability, however, is largely reduced by its high specificity and custom architecture. In this paper we propose much more standardized framework for evolving neural networks, achieving comparable or even better performance in three benchmark problems. We show that tree-based genetic programming (GP) requires only minor modifications to represent and evolve neural networks. Despite its high performance, however, we remain sceptical about the robustness of the proposed method. In a series of further experiments we demonstrate the performance is sensitive to parameter settings and algorithm details. Therefore we refrain from making conclusions about performance of our method and only stress the improvement regarding its simplicity.

3

Programmed death theory revised with artificial evolution

Suchorzewski M., Korzeń M.

Prace Naukowe Politechniki Warszawskiej. Elektronika

|

2007

|

z. 160

269-276

EN

In this we revise the Weismann`s idea of againg and death as adaptive traits. First, we analyse the adaptation process to changing environment of isolated populations (species) having different lifetime and show, that short lifetime may have adaptive value at a population level. Next, we use a Markov chain to model a competition between indyviduals in a finite population. We derive a condition for equilibrium in the population and explain why the long-lived indyviduals usually dominate the population, it would require an extraordinary environment for programmed death to be stable adaptive trait.