English

NL-CNN: A Resources-Constrained Deep Learning Model based on Nonlinear Convolution

Machine Learning 2021-02-03 v1 Computer Vision and Pattern Recognition Neural and Evolutionary Computing

Abstract

A novel convolution neural network model, abbreviated NL-CNN is proposed, where nonlinear convolution is emulated in a cascade of convolution + nonlinearity layers. The code for its implementation and some trained models are made publicly available. Performance evaluation for several widely known datasets is provided, showing several relevant features: i) for small / medium input image sizes the proposed network gives very good testing accuracy, given a low implementation complexity and model size; ii) compares favorably with other widely known resources-constrained models, for instance in comparison to MobileNetv2 provides better accuracy with several times less training times and up to ten times less parameters (memory occupied by the model); iii) has a relevant set of hyper-parameters which can be easily and rapidly tuned due to the fast training specific to it. All these features make NL-CNN suitable for IoT, smart sensing, bio-medical portable instrumentation and other applications where artificial intelligence must be deployed in energy-constrained environments.

Keywords

Cite

@article{arxiv.2102.00227,
  title  = {NL-CNN: A Resources-Constrained Deep Learning Model based on Nonlinear Convolution},
  author = {Radu Dogaru and Ioana Dogaru},
  journal= {arXiv preprint arXiv:2102.00227},
  year   = {2021}
}

Comments

4 pages, reprint submitted to ATEE 2021 conference

R2 v1 2026-06-23T22:40:59.277Z