# Learning Enhancement of CNNs via Separation Index Maximizing at the First Convolutional Layer

arXiv: https://arxiv.org/abs/2201.05217 · HTML: https://mlsanity.com/paper/2201.05217/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 13 Jan 2022.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [All you need is a good init](https://mlsanity.com/paper/1511.06422/) (2015)
- [Data-dependent Initializations of Convolutional Neural Networks](https://mlsanity.com/paper/1511.06856/) (2015)
- [Random Walk Initialization for Training Very Deep Feedforward Networks](https://mlsanity.com/paper/1412.6558/) (2014)
- [Evaluation of Dataflow through layers of Deep Neural Networks in Classification and Regression Problems](https://mlsanity.com/paper/1906.05156/) (2019)

## Abstract (arXiv)

In this paper, a straightforward enhancement learning algorithm based on Separation Index (SI) concept is proposed for Convolutional Neural Networks (CNNs). At first, the SI as a supervised complexity measure is explained its usage in better learning of CNNs for classification problems illustrate. Then, a learning strategy proposes through which the first layer of a CNN is optimized by maximizing the SI, and the further layers are trained through the backpropagation algorithm to learn further layers. In order to maximize the SI at the first layer, A variant of ranking loss is optimized by using the quasi least square error technique. Applying such a learning strategy to some known CNNs and datasets, its enhancement impact in almost all cases is demonstrated.