In this paper, we propose a new scheme for modelling the diverse behavior of neurons. We introduce the conditional activation, in which a neurons activation function is dynamically modified by a control signal. We apply this method to recreate behavior of special neurons existing in the human auditory and visual system. A heterogeneous multilayered perceptron (MLP) incorporating the developed models demonstrates simultaneous improvement in learning speed and performance across a various number of hidden units and layers, compared to a homogeneous network composed of the conventional neuron model. For similar performance, the proposed model lowers the memory for storing network parameters significantly.
@article{arxiv.1803.05006,
title = {Conditional Activation for Diverse Neurons in Heterogeneous Networks},
author = {Albert Lee and Bonnie Lam and Wenyuan Li and Hochul Lee and Wei-Hao Chen and Meng-Fan Chang and Kang. -L. Wang},
journal= {arXiv preprint arXiv:1803.05006},
year = {2018}
}