Operational neural networks
Abstract
Feed-forward, fully connected artificial neural networks or the so-called multi-layer perceptrons are well-known universal approximators. However, their learning performance varies significantly depending on the function or the solution space that they attempt to approximate. This is mainly because of their homogenous configuration based solely on the linear neuron model. Therefore, while they learn very well those problems with a monotonous, relatively simple and linearly separable solution space, they may entirely fail to do so when the solution space is highly nonlinear and complex. Sharing the same linear neuron model with two additional constraints (local connections and weight sharing), this is also true for the conventional convolutional neural networks (CNNs) and it is, therefore, not surprising that in many challenging problems only the deep CNNs with a massive complexity and depth can achieve the required diversity and the learning performance. In order to address this drawback and also to accomplish a more generalized model over the convolutional neurons, this study proposes a novel network model, called operational neural networks (ONNs), which can be heterogeneous and encapsulate neurons with any set of operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data. Finally, the training method to back-propagate the error through the operational layers of ONNs is formulated. Experimental results over highly challenging problems demonstrate the superior learning capabilities of ONNs even with few neurons and hidden layers.
Collections
- Electrical Engineering [2647 items ]
Related items
Showing items related by title, author, creator and subject.
-
Self-organized Operational Neural Networks with Generative Neurons
Kiranyaz, Mustafa Serkan; Malik J.; Abdallah H.B.; Ince T.; Iosifidis A.; Gabbouj M.... more authors ... less authors ( Elsevier Ltd , 2021 , Article)Operational Neural Networks (ONNs) have recently been proposed to address the well-known limitations and drawbacks of conventional Convolutional Neural Networks (CNNs) such as network homogeneity with the sole linear neuron ... -
Real-Time Glaucoma Detection from Digital Fundus Images Using Self-ONNs
Devecioglu O.C.; Malik J.; Ince T.; Kiranyaz, Mustafa Serkan; Atalay E.; Gabbouj M.... more authors ... less authors ( Institute of Electrical and Electronics Engineers Inc. , 2021 , Article)Glaucoma leads to permanent vision disability by damaging the optical nerve that transmits visual images to the brain. The fact that glaucoma does not show any symptoms as it progresses and cannot be stopped at the later ... -
Locality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images
Sirinukunwattana, Korsuk; Raza, Shan E Ahmed; Tsang, Yee-Wah; Snead, David R. J.; Cree, Ian A.; Rajpoot, Nasir M.... more authors ... less authors ( Institute of Electrical and Electronics Engineers Inc. , 2016 , Article)Detection and classification of cell nuclei in histopathology images of cancerous tissue stained with the standard hematoxylin and eosin stain is a challenging task due to cellular heterogeneity. Deep learning approaches ...