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

TL;DR

NL-CNN introduces a nonlinear convolution approach that achieves high accuracy with low complexity, making it ideal for resource-constrained environments like IoT and portable devices.

Contribution

The paper presents NL-CNN, a novel resource-efficient deep learning model with nonlinear convolution, outperforming existing models like MobileNetv2 in accuracy and training efficiency.

Findings

NL-CNN achieves high accuracy on small/medium images with low complexity.

Outperforms MobileNetv2 in accuracy, training time, and parameter count.

Suitable for energy-constrained applications like IoT and biomedical devices.

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.