Header logo is

Developing neural networks with neurons competing for survival

2015

Conference Paper

ei


We study developmental growth in a feedforward neural network model inspired by the survival principle in nature. Each neuron has to select its incoming connections in a way that allow it to fire, as neurons that are not able to fire over a period of time degenerate and die. In order to survive, neurons have to find reoccurring patterns in the activity of the neurons in the preceding layer, because each neuron requires more than one active input at any one time to have enough activation for firing. The sensory input at the lowest layer therefore provides the maximum amount of activation that all neurons compete for. The whole network grows dynamically over time depending on how many patterns can be found and how many neurons can maintain themselves accordingly. We show in simulations that this naturally leads to abstractions in higher layers that emerge in a unsupervised fashion. When evaluating the network in a supervised learning paradigm, it is clear that our network is not competitive. What is interesting though is that this performance was achieved by neurons that simply struggle for survival and do not know about performance error. In contrast to most studies on neural evolution that rely on a network-wide fitness function, our goal was to show that learning behaviour can appear in a system without being driven by any specific utility function or reward signal.

Author(s): Peng, Z and Braun, DA
Pages: 152-153
Year: 2015
Month: August
Publisher: IEEE

Department(s): Empirical Inference
Bibtex Type: Conference Paper (conference)

DOI: 10.1109/DEVLRN.2015.7346133
Event Name: 5th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (IEEE ICDL-EPIROB 2015)
Event Place: Providence, RI, USA

Address: Piscataway, NJ, USA

BibTex

@conference{PengB2015,
  title = {Developing neural networks with neurons competing for survival},
  author = {Peng, Z and Braun, DA},
  pages = {152-153},
  publisher = {IEEE},
  address = {Piscataway, NJ, USA},
  month = aug,
  year = {2015},
  doi = {10.1109/DEVLRN.2015.7346133},
  month_numeric = {8}
}