تقرير
Deep Learning without Global Optimization by Random Fourier Neural Networks
| العنوان: | Deep Learning without Global Optimization by Random Fourier Neural Networks |
|---|---|
| المؤلفون: | Davis, Owen, Geraci, Gianluca, Motamed, Mohammad |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science Mathematics Statistics |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Mathematics - Numerical Analysis, Statistics - Machine Learning, 65T40, 90C15, 65C05, 65C40, 60J22, 68T07 |
| الوصف: | We introduce a new training algorithm for variety of deep neural networks that utilize random complex exponential activation functions. Our approach employs a Markov Chain Monte Carlo sampling procedure to iteratively train network layers, avoiding global and gradient-based optimization while maintaining error control. It consistently attains the theoretical approximation rate for residual networks with complex exponential activation functions, determined by network complexity. Additionally, it enables efficient learning of multiscale and high-frequency features, producing interpretable parameter distributions. Despite using sinusoidal basis functions, we do not observe Gibbs phenomena in approximating discontinuous target functions. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2407.11894 |
| رقم الأكسشن: | edsarx.2407.11894 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |