NL-CNN: A Resources-Constrained Deep Learning Model based on Nonlinear Convolution
This work addresses the need for efficient AI models in IoT, smart sensing, and portable biomedical applications, though it is incremental as it builds on existing convolution and nonlinearity layers.
The authors tackled the problem of deploying deep learning in resource-constrained environments by proposing NL-CNN, a model based on nonlinear convolution, which achieved better accuracy with up to ten times fewer parameters and several times faster training compared to MobileNetv2 on small/medium image datasets.
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.