Correlation Engine 2.0
Clear Search sequence regions

Sizes of these terms reflect their relevance to your search.

The traditional multilayer perceptron (MLP) using a McCulloch-Pitts neuron model is inherently limited to a set of neuronal activities, i.e., linear weighted sum followed by nonlinear thresholding step. Previously, generalized operational perceptron (GOP) was proposed to extend the conventional perceptron model by defining a diverse set of neuronal activities to imitate a generalized model of biological neurons. Together with GOP, a progressive operational perceptron (POP) algorithm was proposed to optimize a predefined template of multiple homogeneous layers in a layerwise manner. In this paper, we propose an efficient algorithm to learn a compact, fully heterogeneous multilayer network that allows each individual neuron, regardless of the layer, to have distinct characteristics. Based on the complexity of the problem, the proposed algorithm operates in a progressive manner on a neuronal level, searching for a compact topology, not only in terms of depth but also width, i.e., the number of neurons in each layer. The proposed algorithm is shown to outperform other related learning methods in extensive experiments on several classification problems.


Dat Thanh Tran, Serkan Kiranyaz, Moncef Gabbouj, Alexandros Iosifidis. Heterogeneous Multilayer Generalized Operational Perceptron. IEEE transactions on neural networks and learning systems. 2020 Mar;31(3):710-724

Expand section icon Mesh Tags

PMID: 31170081

View Full Text