Updating the standard neuron model in artificial neural networks

The article presents an updated neuron model for artificial neural networks, replacing the traditional point neuron model with a more realistic cortical cell model. Theoretical analyses and experimental results indicate that this new model enhances expressivity, robustness, and learning speed, while also reducing memorization and training data requirements, all without increasing the number of parameters. This advancement is significant for practitioners as it suggests potential improvements in neural network performance and efficiency, warranting consideration in future ANN designs.