Progressive Operational Perceptrons with Memory

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

  • Dat Thanh Tran, Tampere University of Technology
  • ,
  • Serkan Kiranyaz, Qatar University, Doha
  • ,
  • Moncef Gabbouj, Tampere University of Technology
  • ,
  • Alexandros Iosifidis

Generalized Operational Perceptron (GOP) was proposed to generalize the linear neuron model used in the traditional Multilayer Perceptron (MLP) by mimicking the synaptic connections of biological neurons showing nonlinear neurochemical behaviours. Previously, Progressive Operational Perceptron (POP) was proposed to train a multilayer network of GOPs which is formed layer-wise in a progressive manner. While achieving superior learning performance over other types of networks, POP has a high computational complexity. In this work, we propose POPfast, an improved variant of POP that signicantly reduces the computational complexity of POP, thus accelerating the training time of GOP networks. In addition, we also propose major architectural modications of POPfast that can augment the progressive learning process of POP by incorporating an information preserving, linear projection path from the input to the output layer at each progressive step. The proposed extensions can be interpreted as a mechanism that provides direct information extracted from the previously learned layers to the network, hence the term “memory”. This allows the network to learn deeper architectures and better data representations. An extensive set of experiments in human action, object, facial identity and scene recognition problems demonstrates that the proposed algorithms can train GOP networks much faster than POPs while achieving better performance compared to original POPs and other related algorithms.

Original languageEnglish
Pages (from-to)172-181
Number of pages10
Publication statusPublished - 28 Feb 2020

    Research areas

  • Generalized operational perceptron, Neural architecture learning, Progressive learning

See relations at Aarhus University Citationformats

ID: 173481176