Updating the standard neuron model in artificial neural networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917554780372992 |
|---|---|
| author | Mohedano, Raul Batard, Thomas Velasco-Salido, Erik Mendoza, Ramsses De Los Santos Martínez, Jorge H. Levine, Stacey Bertalmío, Marcelo |
| author_facet | Mohedano, Raul Batard, Thomas Velasco-Salido, Erik Mendoza, Ramsses De Los Santos Martínez, Jorge H. Levine, Stacey Bertalmío, Marcelo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30370 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Updating the standard neuron model in artificial neural networks Mohedano, Raul Batard, Thomas Velasco-Salido, Erik Mendoza, Ramsses De Los Santos Martínez, Jorge H. Levine, Stacey Bertalmío, Marcelo Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Updating the standard neuron model in artificial neural networks |
| topic | Neural and Evolutionary Computing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2605.30370 |