# Strengthening the Training of Convolutional Neural Networks By Using Walsh Matrix

arXiv: https://arxiv.org/abs/2104.00035 · HTML: https://mlsanity.com/paper/2104.00035/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 67 references that are in the map.
- First posted on arXiv 31 Mar 2021.

## Builds on (most cited first, 7 of 7)

- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [ECG Heartbeat Classification: A Deep Transferable Representation](https://mlsanity.com/paper/1805.00794/) (2018)
- [Fractional Max-Pooling](https://mlsanity.com/paper/1412.6071/) (2014)
- [ECG arrhythmia classification using a 2-D convolutional neural network](https://mlsanity.com/paper/1804.06812/) (2018)
- [A Comparison of 1-D and 2-D Deep Convolutional Neural Networks in ECG Classification](https://mlsanity.com/paper/1810.07088/) (2018)
- [Towards Asynchronous Motor Imagery-Based Brain-Computer Interfaces: a joint training scheme using deep learning](https://mlsanity.com/paper/1808.10852/) (2018)
- [Classification of Motor Imagery EEG Signals by Using a Divergence Based Convolutional Neural Network](https://mlsanity.com/paper/2103.10977/) (2021)

## Built on by (most cited first, 3 of 3)

- [Generating Ten BCI Commands Using Four Simple Motor Imageries](https://mlsanity.com/paper/2105.14493/) (2021)
- [Classification of Hyperspectral Images by Using Spectral Data and Fully Connected Neural Network](https://mlsanity.com/paper/2201.02821/) (2022)
- [Negotiated Representations to Prevent Forgetting in Machine Learning Applications](https://mlsanity.com/paper/2312.00237/) (2023)

## Abstract (arXiv)

DNN structures are continuously developing and achieving high performances in classification problems. Also, it is observed that success rates obtained with DNNs are higher than those obtained with traditional neural networks. In addition, one of the advantages of DNNs is that there is no need to spend an extra effort to determine the features; the CNN automatically extracts the features from the dataset during the training. Besides their benefits, the DNNs have the following three major drawbacks among the others: (i) Researchers have struggled with over-fitting and under-fitting issues in the training of DNNs, (ii) determination of even a coarse structure for the DNN may take days, and (iii) most of the time, the proposed network structure is too large to be too bulky to be used in real time applications. We have modified the training and structure of DNN to increase the classification performance, to decrease the number of nodes in the structure, and to be used with less number of hyper parameters. A minimum distance network (MDN) following the last layer of the convolutional neural network (CNN) is used as the classifier instead of a fully connected neural network (FCNN). In order to strengthen the training of the CNN, we suggest employing Walsh function. We tested the performances of the proposed DNN (named as DivFE) on the classification of ECG, EEG, heart sound, detection pneumonia in X-ray chest images, detection of BGA solder defects, and patterns of benchmark datasets (MNIST, IRIS, CIFAR10 and CIFAR20). In different areas, it has been observed that a higher classification performance was obtained by using the DivFE with less number of nodes.