Updating the standard neuron model in artificial neural networks
This work addresses the fundamental limitation of the simplistic point neuron model in ANNs, potentially benefiting all users of neural networks by improving their core building block.
This paper updates the standard point neuron model in ANNs with a more recent cortical cell model. This change, without increasing parameters, leads to improved expressivity, robustness, and learning speed, while reducing memorization and data requirements.
From their inception in the 1950s, artificial neural networks (ANNs) started using the so-called point neuron model then prevalent in neuroscience, hoping that this analogy would allow for a better emulation of brain function. Over the years the neuroscience literature has shown that the point neuron model is too simplistic to properly represent many fundamental neural processes; however, the standard neuron model in ANNs still remains the same. Here we substitute it by a very recent model of cortical cells and demonstrate through theoretical analyses and experimental results how, simply by using a more realistic neural unit element without augmenting the number of parameters, the resulting ANNs offer a number of important advantages that include increases in expressivity, robustness and learning speed, and a reduction in memorization and the amount of training data needed.