Full-Precision and Ternarised Neural Networks with Tunnel-Diode Activation Functions: Computing and Physics Perspectives
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912758819192832 |
|---|---|
| author | McNaughton, Jake Abbas, A. H. Maksymov, Ivan S. |
| author_facet | McNaughton, Jake Abbas, A. H. Maksymov, Ivan S. |
| contents | The mathematical complexity and high dimensionality of neural networks slow both training and deployment, demanding heavy computational resources. This has driven the search for alternative architectures built from novel components, including new activation functions. Taking a different approach from state-of-the-art neural and neuromorphic computational systems, we employ the current-voltage characteristic of a tunnel diode as a quantum physics-based activation function for deep networks. This tunnel-diode activation function (TDAF) outperforms standard activations in deep architectures, delivering lower loss and higher accuracy in both training and evaluation. We also highlight its promise for implementation in electronic hardware aimed at neuromorphic, ternarised and energy efficient AI systems. Speaking broadly, our work lays a solid foundation for a new bridge between machine learning, semiconductor electronics and quantum physics -- bringing together quantum tunnelling, a phenomenon recognised in six Nobel Prizes (including the 2025 award), and contemporary AI research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04978 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Full-Precision and Ternarised Neural Networks with Tunnel-Diode Activation Functions: Computing and Physics Perspectives McNaughton, Jake Abbas, A. H. Maksymov, Ivan S. Applied Physics Machine Learning The mathematical complexity and high dimensionality of neural networks slow both training and deployment, demanding heavy computational resources. This has driven the search for alternative architectures built from novel components, including new activation functions. Taking a different approach from state-of-the-art neural and neuromorphic computational systems, we employ the current-voltage characteristic of a tunnel diode as a quantum physics-based activation function for deep networks. This tunnel-diode activation function (TDAF) outperforms standard activations in deep architectures, delivering lower loss and higher accuracy in both training and evaluation. We also highlight its promise for implementation in electronic hardware aimed at neuromorphic, ternarised and energy efficient AI systems. Speaking broadly, our work lays a solid foundation for a new bridge between machine learning, semiconductor electronics and quantum physics -- bringing together quantum tunnelling, a phenomenon recognised in six Nobel Prizes (including the 2025 award), and contemporary AI research. |
| title | Full-Precision and Ternarised Neural Networks with Tunnel-Diode Activation Functions: Computing and Physics Perspectives |
| topic | Applied Physics Machine Learning |
| url | https://arxiv.org/abs/2503.04978 |