Fast Reversible Learning based on Neurons functioning as Anisotropic Multiplex Hubs

@inproceedings{Vardi2017FastRL,
  title={Fast Reversible Learning based on Neurons functioning as Anisotropic Multiplex Hubs},
  author={Roni Vardi and Amir Goldental and Anton Sheinin and Shira Sardi and Ido Kanter},
  year={2017}
}
Neural networks are composed of neurons and synapses, which are responsible for learning in a slow adaptive dynamical process. Here we experimentally show that neurons act like independent anisotropic multiplex hubs, which relay and mute incoming signals following their input directions. Theoretically, the observed information routing enriches the computational capabilities of neurons by allowing, for instance, equalization among different information routes in the network, as well as high… CONTINUE READING
Tweets
This paper has been referenced on Twitter 6 times. VIEW TWEETS