Shahrood University of Technology Journal of AI and Data Mining 2322-5211 14 1 2026 01 01 K-means-CRBM: An Efficient Unsupervised Tool for Feature Learning 61 69 3678 10.22044/jadm.2025.16416.2767 EN Reza Kharghanian Faculty of Electrical Engineering, Shahrood University of Technology, Shahrood, Iran. 0000-0002-4033-7156 Zeynab Mohammadpoory Faculty of Electrical Engineering, Shahrood University of Technology, Shahrood, Iran. Journal Article 2025 06 26 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.<br />Experiments on MNIST, CIFAR10, 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. Convolutional Restricted Boltzmann Machine Feature learning representation learning K-means clustering https://jad.shahroodut.ac.ir/article_3678_7376c368c5fa7b3f90d65917a620079e.pdf