Operational neural networks

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

  • Serkan Kiranyaz, Qatar University
  • ,
  • Turker Ince, Izmir Ekonomi University
  • ,
  • Alexandros Iosifidis
  • Moncef Gabbouj, Tampereen Yliopisto

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.

Original languageEnglish
JournalNeural Computing and Applications
Volume32
Issue11
Pages (from-to)6645-6668
Number of pages24
ISSN0941-0643
DOIs
Publication statusPublished - 2020

    Research areas

  • Convolutional neural networks, Heterogeneous and nonlinear neural networks, Operational neural network

See relations at Aarhus University Citationformats

ID: 187179966