Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2509.15316 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918144107347968 |
|---|---|
| author | Armeniakos, Giorgos Mantzakidis, Theodoros Soudris, Dimitrios |
| author_facet | Armeniakos, Giorgos Mantzakidis, Theodoros Soudris, Dimitrios |
| contents | Printed Electronics (PE) provide a flexible, cost-efficient alternative to silicon for implementing machine learning (ML) circuits, but their large feature sizes limit classifier complexity. Leveraging PE's low fabrication and NRE costs, designers can tailor hardware to specific ML models, simplifying circuit design. This work explores alternative arithmetic and proposes a hybrid unary-binary architecture that removes costly encoders and enables efficient, multiplier-less execution of MLP classifiers. We also introduce architecture-aware training to further improve area and power efficiency. Evaluation on six datasets shows average reductions of 46% in area and 39% in power, with minimal accuracy loss, surpassing other state-of-the-art MLP designs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_15316 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrid unary-binary design for multiplier-less printed Machine Learning classifiers Armeniakos, Giorgos Mantzakidis, Theodoros Soudris, Dimitrios Machine Learning Printed Electronics (PE) provide a flexible, cost-efficient alternative to silicon for implementing machine learning (ML) circuits, but their large feature sizes limit classifier complexity. Leveraging PE's low fabrication and NRE costs, designers can tailor hardware to specific ML models, simplifying circuit design. This work explores alternative arithmetic and proposes a hybrid unary-binary architecture that removes costly encoders and enables efficient, multiplier-less execution of MLP classifiers. We also introduce architecture-aware training to further improve area and power efficiency. Evaluation on six datasets shows average reductions of 46% in area and 39% in power, with minimal accuracy loss, surpassing other state-of-the-art MLP designs. |
| title | Hybrid unary-binary design for multiplier-less printed Machine Learning classifiers |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.15316 |