# Weight Freezing: A Regularization Approach for Fully Connected Layers with an Application in EEG Classification

arXiv: https://arxiv.org/abs/2306.05775 · HTML: https://mlsanity.com/paper/2306.05775/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 37 references that are in the map.
- First posted on arXiv 9 Jun 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Dropout Training as Adaptive Regularization](https://mlsanity.com/paper/1307.1493/) (2013)
- [Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach](https://mlsanity.com/paper/1808.05464/) (2018)
- [Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks](https://mlsanity.com/paper/2201.03299/) (2022)
- [Towards Dropout Training for Convolutional Neural Networks](https://mlsanity.com/paper/1512.00242/) (2015)
- [Priming Cross-Session Motor Imagery Classification with A Universal Deep Domain Adaptation Framework](https://mlsanity.com/paper/2202.09559/) (2022)

## Built on by (most cited first, 2 of 2)

- [Enhancing Motor Imagery Decoding in Brain Computer Interfaces using Riemann Tangent Space Mapping and Cross Frequency Coupling](https://mlsanity.com/paper/2310.19198/) (2023)
- [Pseudo Channel: Time Embedding for Motor Imagery Decoding](https://mlsanity.com/paper/2405.15812/) (2024)

## Abstract (arXiv)

In the realm of EEG decoding, enhancing the performance of artificial neural networks (ANNs) carries significant potential. This study introduces a novel approach, termed "weight freezing", that is anchored on the principles of ANN regularization and neuroscience prior knowledge. The concept of weight freezing revolves around the idea of reducing certain neurons' influence on the decision-making process for a specific EEG task by freezing specific weights in the fully connected layer during the backpropagation process. This is actualized through the use of a mask matrix and a threshold to determine the proportion of weights to be frozen during backpropagation. Moreover, by setting the masked weights to zero, weight freezing can not only realize sparse connections in networks with a fully connected layer as the classifier but also function as an efficacious regularization method for fully connected layers. Through experiments involving three distinct ANN architectures and three widely recognized EEG datasets, we validate the potency of weight freezing. Our method significantly surpasses previous peak performances in classification accuracy across all examined datasets. Supplementary control experiments offer insights into performance differences pre and post weight freezing implementation and scrutinize the influence of the threshold in the weight freezing process. Our study underscores the superior efficacy of weight freezing compared to traditional fully connected networks for EEG feature classification tasks. With its proven effectiveness, this innovative approach holds substantial promise for contributing to future strides in EEG decoding research.