K-means-CRBM: An Efficient Unsupervised Tool for Feature Learning

The Convolutional Restricted Boltzmann Machine (CRBM) is a generative model that extracts representations from unlabeled data, achieving success in various applications. However, its unsupervised nature may yield suboptimal representations for specific classification tasks. This paper proposes adapting k-means clustering to enhance CRBM parameters, aligning features with informative cluster centers. A novel criterion combining generative and soft-K-Means objectives optimizes both cluster centers and CRBM parameters, allowing for continued unsupervised feature learning.Experiments on MNIST, CIFAR۱۰, and three facial expression datasets (JAFFE, KANADE, BU) show that the proposed method enhances the learning process and offers a more informative representation compared to standard and classification CRBM.

کلیدواژه ها:

Convolutional Restricted Boltzmann Machine ، Feature learning ، representation learning ، K-means clustering