Progressive Operational Perceptrons
المؤلف | Kiranyaz, Mustafa Serkan |
المؤلف | Ince T. |
المؤلف | Iosifidis A. |
المؤلف | Gabbouj M. |
تاريخ الإتاحة | 2022-04-26T12:31:22Z |
تاريخ النشر | 2017 |
اسم المنشور | Neurocomputing |
المصدر | Scopus |
المعرّف | http://dx.doi.org/10.1016/j.neucom.2016.10.044 |
الملخص | There are well-known limitations and drawbacks on the performance and robustness of the feed-forward, fully-connected Artificial Neural Networks (ANNs), or the so-called Multi-Layer Perceptrons (MLPs). In this study we shall address them by Generalized Operational Perceptrons (GOPs) that consist of neurons with distinct (non-)linear operators to achieve a generalized model of the biological neurons and ultimately a superior diversity. We modified the conventional back-propagation (BP) to train GOPs and furthermore, proposed Progressive Operational Perceptrons (POPs) to achieve self-organized and depth-adaptive GOPs according to the learning problem. The most crucial property of the POPs is their ability to simultaneously search for the optimal operator set and train each layer individually. The final POP is, therefore, formed layer by layer and in this paper we shall show that this ability enables POPs with minimal network depth to attack the most challenging learning problems that cannot be learned by conventional ANNs even with a deeper and significantly complex configuration. Experimental results show that POPs can scale up very well with the problem size and can have the potential to achieve a superior generalization performance on real benchmark problems with a significant gain. |
اللغة | en |
الناشر | Elsevier B.V. |
الموضوع | Benchmarking Complex networks Cybernetics Mathematical operators Neural networks Scalability Bench-mark problems Complex configuration Diversity Generalization performance Generalized models Multi-layer perceptrons Multi-layer perceptrons (MLPs) Optimal operators Backpropagation Article artificial neural network back propagation generalized operational perceptron learning disorder linear system mathematical analysis mathematical computing mathematical parameters nerve cell perceptron priority journal progressive operational perceptron statistical model |
النوع | Article |
الصفحات | 142-154 |
رقم المجلد | 224 |
تحقق من خيارات الوصول
الملفات في هذه التسجيلة
الملفات | الحجم | الصيغة | العرض |
---|---|---|---|
لا توجد ملفات لها صلة بهذه التسجيلة. |
هذه التسجيلة تظهر في المجموعات التالية
-
الهندسة الكهربائية [2611 items ]