Report
Histogram-Equalized Quantization for logic-gated Residual Neural Networks
| العنوان: | Histogram-Equalized Quantization for logic-gated Residual Neural Networks |
|---|---|
| المؤلفون: | Nguyen, Van Thien, Guicquero, William, Sicard, Gilles |
| المصدر: | 2022 IEEE International Symposium on Circuits and Systems (ISCAS), Austin, TX, USA, 2022, pp. 1289-1293 |
| سنة النشر: | 2025 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Hardware Architecture |
| الوصف: | Adjusting the quantization according to the data or to the model loss seems mandatory to enable a high accuracy in the context of quantized neural networks. This work presents Histogram-Equalized Quantization (HEQ), an adaptive framework for linear symmetric quantization. HEQ automatically adapts the quantization thresholds using a unique step size optimization. We empirically show that HEQ achieves state-of-the-art performances on CIFAR-10. Experiments on the STL-10 dataset even show that HEQ enables a proper training of our proposed logic-gated (OR, MUX) residual networks with a higher accuracy at a lower hardware complexity than previous work. Comment: Published at IEEE ISCAS 2022 |
| نوع الوثيقة: | Working Paper |
| DOI: | 10.1109/ISCAS48785.2022.9937290 |
| URL الوصول: | http://arxiv.org/abs/2501.04517 |
| رقم الانضمام: | edsarx.2501.04517 |
| قاعدة البيانات: | arXiv |
| DOI: | 10.1109/ISCAS48785.2022.9937290 |
|---|