Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2605.10474 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910209154220032 |
|---|---|
| author | Abu-Haeyeh, Yasmine Ladner, Tobias Althoff, Matthias Hedrich, Lars |
| author_facet | Abu-Haeyeh, Yasmine Ladner, Tobias Althoff, Matthias Hedrich, Lars |
| contents | Analog neural networks are gaining attention due to their efficiency in terms of power consumption and processing speed. However, since analog neural networks are implemented as physical circuits, they are highly sensitive to manufacturing process variations, which can cause large deviations from the nominal model. We present a polynomial-based model that resembles the performance of the neuron circuit under process variations. Then, we formally verify the behavior of the circuit-level model using reachability analysis with polynomial zonotopes, thus, avoiding conventional, time-consuming Monte Carlo simulations. We evaluate our proposed verification approach on three different datasets, verifying both fully-connected and convolutional analog neural networks. Our experimental results confirm the effectiveness of our verification approach by reducing the verification time from days to seconds while enclosing 99% of the variation samples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10474 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Formally Verifying Analog Neural Networks Under Process Variations Using Polynomial Zonotopes Abu-Haeyeh, Yasmine Ladner, Tobias Althoff, Matthias Hedrich, Lars Machine Learning Artificial Intelligence Analog neural networks are gaining attention due to their efficiency in terms of power consumption and processing speed. However, since analog neural networks are implemented as physical circuits, they are highly sensitive to manufacturing process variations, which can cause large deviations from the nominal model. We present a polynomial-based model that resembles the performance of the neuron circuit under process variations. Then, we formally verify the behavior of the circuit-level model using reachability analysis with polynomial zonotopes, thus, avoiding conventional, time-consuming Monte Carlo simulations. We evaluate our proposed verification approach on three different datasets, verifying both fully-connected and convolutional analog neural networks. Our experimental results confirm the effectiveness of our verification approach by reducing the verification time from days to seconds while enclosing 99% of the variation samples. |
| title | Formally Verifying Analog Neural Networks Under Process Variations Using Polynomial Zonotopes |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.10474 |