Algorithms and data structures for automatic precision estimation of neural networks
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911183683977216 |
|---|---|
| author | Netay, Igor V. |
| author_facet | Netay, Igor V. |
| contents | We describe algorithms and data structures to extend a neural network library with automatic precision estimation for floating point computations. We also discuss conditions to make estimations exact and preserve high computation performance of neural networks training and inference. Numerical experiments show the consequences of significant precision loss for particular values such as inference, gradients and deviations from mathematically predicted behavior.
It turns out that almost any neural network accumulates computational inaccuracies. As a result, its behavior does not coincide with predicted by the mathematical model of neural network. This shows that tracking of computational inaccuracies is important for reliability of inference, training and interpretability of results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24607 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Algorithms and data structures for automatic precision estimation of neural networks Netay, Igor V. Data Structures and Algorithms Artificial Intelligence Machine Learning Numerical Analysis We describe algorithms and data structures to extend a neural network library with automatic precision estimation for floating point computations. We also discuss conditions to make estimations exact and preserve high computation performance of neural networks training and inference. Numerical experiments show the consequences of significant precision loss for particular values such as inference, gradients and deviations from mathematically predicted behavior. It turns out that almost any neural network accumulates computational inaccuracies. As a result, its behavior does not coincide with predicted by the mathematical model of neural network. This shows that tracking of computational inaccuracies is important for reliability of inference, training and interpretability of results. |
| title | Algorithms and data structures for automatic precision estimation of neural networks |
| topic | Data Structures and Algorithms Artificial Intelligence Machine Learning Numerical Analysis |
| url | https://arxiv.org/abs/2509.24607 |