The Neuromorphic Supremacy
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_ | 1866914622152376320 |
|---|---|
| author | Tsybina, Yuliya Tyukin, Ivan Y. Gorban, Alexander N. Kazantsev, Victor Wang, Dianhui Gordleeva, Susanna |
| author_facet | Tsybina, Yuliya Tyukin, Ivan Y. Gorban, Alexander N. Kazantsev, Victor Wang, Dianhui Gordleeva, Susanna |
| contents | Live neural systems demonstrate remarkable capabilities to learn new behavior and patterns from mere few examples and are known to operate robustly under severe sensory noise. These capabilities, however, remain largely out of reach for modern artificial neural networks, including deep learning models. We show that this gap can be bridged by embedding novel genuine neuromorphic circuits into conventional artificial neural network architectures. These circuits comprise astrocytic modulation and spiking dynamics inherent to biological neural structures. Tested across standard benchmarks representing tasks of varying complexity, the hybrid models achieve high accuracy from few training examples per class and sustain high performance under occlusion and impulse noise that cause performance collapse in standard models without neuromorphic adaptation. We term this phenomenon neuromorphic supremacy - a regime in which architectures grounded in neurobiology decisively outperform classical deep learning, pointing toward a principled foundation for perception in embodied AI systems operating in noisy, data-scarce environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01841 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Neuromorphic Supremacy Tsybina, Yuliya Tyukin, Ivan Y. Gorban, Alexander N. Kazantsev, Victor Wang, Dianhui Gordleeva, Susanna Neurons and Cognition Live neural systems demonstrate remarkable capabilities to learn new behavior and patterns from mere few examples and are known to operate robustly under severe sensory noise. These capabilities, however, remain largely out of reach for modern artificial neural networks, including deep learning models. We show that this gap can be bridged by embedding novel genuine neuromorphic circuits into conventional artificial neural network architectures. These circuits comprise astrocytic modulation and spiking dynamics inherent to biological neural structures. Tested across standard benchmarks representing tasks of varying complexity, the hybrid models achieve high accuracy from few training examples per class and sustain high performance under occlusion and impulse noise that cause performance collapse in standard models without neuromorphic adaptation. We term this phenomenon neuromorphic supremacy - a regime in which architectures grounded in neurobiology decisively outperform classical deep learning, pointing toward a principled foundation for perception in embodied AI systems operating in noisy, data-scarce environments. |
| title | The Neuromorphic Supremacy |
| topic | Neurons and Cognition |
| url | https://arxiv.org/abs/2606.01841 |