تقرير
Activations Through Extensions: A Framework To Boost Performance Of Neural Networks
| العنوان: | Activations Through Extensions: A Framework To Boost Performance Of Neural Networks |
|---|---|
| المؤلفون: | Kamanchi, Chandramouli, Mukherjee, Sumanta, Sampath, Kameshwaran, Dayama, Pankaj, Jati, Arindam, Ekambaram, Vijay, Phan, Dzung |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science Mathematics |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary Computing, Mathematics - Numerical Analysis |
| الوصف: | Activation functions are non-linearities in neural networks that allow them to learn complex mapping between inputs and outputs. Typical choices for activation functions are ReLU, Tanh, Sigmoid etc., where the choice generally depends on the application domain. In this work, we propose a framework/strategy that unifies several works on activation functions and theoretically explains the performance benefits of these works. We also propose novel techniques that originate from the framework and allow us to obtain ``extensions'' (i.e. special generalizations of a given neural network) of neural networks through operations on activation functions. We theoretically and empirically show that ``extensions'' of neural networks have performance benefits compared to vanilla neural networks with insignificant space and time complexity costs on standard test functions. We also show the benefits of neural network ``extensions'' in the time-series domain on real-world datasets. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2408.03599 |
| رقم الأكسشن: | edsarx.2408.03599 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |