A Hybrid Multi-Well Hopfield-CNN with Feature Extraction and K-Means for MNIST Classification

TL;DR

This paper introduces a hybrid model combining CNN feature extraction, k-means clustering, and a multi-well Hopfield network for classifying MNIST digits, achieving high accuracy and interpretability.

Contribution

It proposes a novel hybrid framework that integrates deep learning, clustering, and energy-based neural networks for improved digit classification.

Findings

Achieved 99.2% test accuracy on MNIST.

Demonstrated robustness to handwriting variability.

Highlighted importance of feature extraction and prototype coverage.

Abstract

This study presents a hybrid model for classifying handwritten digits in the MNIST dataset, combining convolutional neural networks (CNNs) with a multi-well Hopfield network. The approach employs a CNN to extract high-dimensional features from input images, which are then clustered into class-specific prototypes using k-means clustering. These prototypes serve as attractors in a multi-well energy landscape, where a Hopfield network performs classification by minimizing an energy function that balances feature similarity and class assignment.The model's design enables robust handling of intraclass variability, such as diverse handwriting styles, while providing an interpretable framework through its energy-based decision process. Through systematic optimization of the CNN architecture and the number of wells, the model achieves a high test accuracy of 99.2% on 10,000 MNIST images, demonstrating its effectiveness for image classification tasks. The findings highlight the critical role of deep feature extraction and sufficient prototype coverage in achieving high performance, with potential for broader applications in pattern recognition.