Evolving autonomous learning in cognitive networks
| Autor: | Arend Hintze, Leigh Sheneman |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
0301 basic medicine
Cognitive model Computer science brain lcsh:Medicine Article human experiment 03 medical and health sciences 0302 clinical medicine Genetic algorithm human lcsh:Science logic Multidisciplinary Markov chain Artificial neural network Computer Sciences business.industry lcsh:R SIGNAL (programming language) article Probabilistic logic Cognitive network machine learning Datavetenskap (datalogi) 030104 developmental biology lcsh:Q Artificial intelligence business 030217 neurology & neurosurgery |
| Zdroj: | Scientific Reports Scientific Reports, Vol 7, Iss 1, Pp 1-11 (2017) |
| ISSN: | 2045-2322 |
| Popis: | There are two common approaches for optimizing the performance of a machine: genetic algorithms and machine learning. A genetic algorithm is applied over many generations whereas machine learning works by applying feedback until the system meets a performance threshold. These methods have been previously combined, particularly in artificial neural networks using an external objective feedback mechanism. We adapt this approach to Markov Brains, which are evolvable networks of probabilistic and deterministic logic gates. Prior to this work MB could only adapt from one generation to the other, so we introduce feedback gates which augment their ability to learn during their lifetime. We show that Markov Brains can incorporate these feedback gates in such a way that they do not rely on an external objective feedback signal, but instead can generate internal feedback that is then used to learn. This results in a more biologically accurate model of the evolution of learning, which will enable us to study the interplay between evolution and learning and could be another step towards autonomously learning machines. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|