Maximizing Computational Power by Neuroevolution
| Thesis title in Czech: | Maximalizace výpočetní síly neuroevolucí |
|---|---|
| Thesis title in English: | Maximizing Computational Power by Neuroevolution |
| Key words: | neuronové sítě, echo state networks, genetické algoritmy, neuroevoluce, hranice chaosu |
| English key words: | neural networks, echo state networks, genetic algorithms, neuroevolution, edge of chaos, phase transition |
| Academic year of topic announcement: | 2015/2016 |
| Thesis type: | diploma thesis |
| Thesis language: | angličtina |
| Department: | Department of Software and Computer Science Education (32-KSVI) |
| Supervisor: | RNDr. František Mráz, CSc. |
| Author: | hidden - assigned and confirmed by the Study Dept. |
| Date of registration: | 31.03.2016 |
| Date of assignment: | 31.03.2016 |
| Confirmed by Study dept. on: | 07.04.2016 |
| Date and time of defence: | 12.09.2016 10:00 |
| Date of electronic submission: | 28.07.2016 |
| Date of submission of printed version: | 28.07.2016 |
| Date of proceeded defence: | 12.09.2016 |
| Opponents: | doc. Mgr. Martin Pilát, Ph.D. |
| Guidelines |
| Neural networks are capable of solving quite complex tasks. A recent study revealed that randomly generated recurrent neural networks called echo state networks achieve highest computational power when their dynamics approaches the transition between stable and chaotic behaviour. The goal of the thesis is to compare computational power of randomly generated echo state networks with neural networks evolved using neuroevolution. |
| References |
| Bertschinger, N., Natschläger, T.: Real-time computation at the edge of chaos in recurrent neural networks. Neural Computation 16.7 (2004):1413–1436.
Boedecker, J., et al.: Information processing in echo state networks at the edge of chaos. Theory in Biosciences 131.3 (2012):205-213. Stanley, K. O., and Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary computation 10.2 (2002):99-127. |