کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
6863283 | 678063 | 2015 | 20 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
A new class of multi-stable neural networks: Stability analysis and learning process
ترجمه فارسی عنوان
یک کلاس جدید از شبکه های عصبی چند ثبات: تجزیه و تحلیل ثبات و روند یادگیری
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
هوش مصنوعی
چکیده انگلیسی
Recently, multi-stable Neural Networks (NN) with exponential number of attractors have been presented and analyzed theoretically; however, the learning process of the parameters of these systems while considering stability conditions and specifications of real world problems has not been studied. In this paper, a new class of multi-stable NNs using sinusoidal dynamics with exponential number of attractors is introduced. The sufficient conditions for multi-stability of the proposed system are posed using Lyapunov theorem. In comparison to the other methods in this class of multi-stable NNs, the proposed method is used as a classifier by applying a learning process with respect to the topological information of data and conditions of Lyapunov multi-stability. The proposed NN is applied on both synthetic and real world datasets with an accuracy comparable to classical classifiers.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neural Networks - Volume 65, May 2015, Pages 53-64
Journal: Neural Networks - Volume 65, May 2015, Pages 53-64
نویسندگان
E. Bavafaye Haghighi, G. Palm, M. Rahmati, M.J. Yazdanpanah,