Loading...
Please wait, while we are loading the content...
Similar Documents
NeuroEvolution : The Importance of Transfer Function Evolution and Heterogeneous Networks
| Content Provider | Semantic Scholar |
|---|---|
| Author | Turner, Andrew James Miller, Julian Francis |
| Copyright Year | 2014 |
| Abstract | NeuroEvolution is the application of Evolutionary Algorithms to the training of Artificial Neural Networks. Currently the vast majority of NeuroEvolutionary methods create homogeneous networks of user defined transfer functions. This is despite NeuroEvolution being capable of creating heterogeneous networks where each neuron’s transfer function is not chosen by the user, but selected or optimised during evolution. This paper demonstrates how NeuroEvolution can be used to select or optimise each neuron’s transfer function and empirically shows that doing so significantly aids training. This result is important as most NeuroEvolutionary methods are capable of creating heterogeneous networks using the methods described. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://doc.gold.ac.uk/aisb50/AISB50-S11/AISB50-S11-Turner-paper.pdf |
| Alternate Webpage(s) | http://www.cartesiangp.co.uk/papers/aisb2014-turner.pdf |
| Language | English |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
