Hopfield-Enhanced Deep Neural Networks for Artifact-Resilient Brain State Decoding

TL;DR

This paper introduces a hybrid Hopfield-CNN framework that enhances brain state decoding accuracy from noisy neural recordings, demonstrating improved robustness over traditional CNN models in artifact-laden data.

Contribution

The study presents a novel two-stage approach combining Hopfield Networks with CNNs to effectively preprocess artifacts and classify brain states in noisy neural data.

Findings

The hybrid model outperforms standalone CNNs in noisy conditions.

The framework achieves parity with clean-data CNNs at lower noise levels.

It enhances robustness for small-scale neural recording experiments.

Abstract

The study of brain states, ranging from highly synchronous to asynchronous neuronal patterns like the sleep-wake cycle, is fundamental for assessing the brain's spatiotemporal dynamics and their close connection to behavior. However, the development of new techniques to accurately identify them still remains a challenge, as these are often compromised by the presence of noise, artifacts, and suboptimal recording quality. In this study, we propose a two-stage computational framework combining Hopfield Networks for artifact data preprocessing with Convolutional Neural Networks (CNNs) for classification of brain states in rat neural recordings under different levels of anesthesia. To evaluate the robustness of our framework, we deliberately introduced noise artifacts into the neural recordings. We evaluated our hybrid Hopfield-CNN pipeline by benchmarking it against two comparative models: a standalone CNN handling the same noisy inputs, and another CNN trained and tested on artifact-free data. Performance across various levels of data compression and noise intensities showed that our framework can effectively mitigate artifacts, allowing the model to reach parity with the clean-data CNN at lower noise levels. Although this study mainly benefits small-scale experiments, the findings highlight the necessity for advanced deep learning and Hopfield Network models to improve scalability and robustness in diverse real-world settings.