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

arXiv: https://arxiv.org/abs/2102.00227 · HTML: https://mlsanity.com/paper/2102.00227/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 16 references that are in the map.
- First posted on arXiv 30 Jan 2021.

## Builds on (most cited first, 6 of 6)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Non-linear Convolution Filters for CNN-based Learning](https://mlsanity.com/paper/1708.07038/) (2017)
- [Fruit recognition from images using deep learning](https://mlsanity.com/paper/1712.00580/) (2017)
- [Facial Expression Recognition using Convolutional Neural Networks: State of the Art](https://mlsanity.com/paper/1612.02903/) (2016)
- [EffNet: An Efficient Structure for Convolutional Neural Networks](https://mlsanity.com/paper/1801.06434/) (2018)

## Built on by (most cited first, 1 of 1)

- [LB-CNN: An Open Source Framework for Fast Training of Light Binary Convolutional Neural Networks using Chainer and Cupy](https://mlsanity.com/paper/2106.15350/) (2021)

## Abstract (arXiv)

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.