Deep Learning with Nonparametric Clustering

Abstract

Clustering is an essential problem in machine learning and data mining. One vital factor that impacts clustering performance is how to learn or design the data representation (or features). Fortunately, recent advances in deep learning can learn unsupervised features effectively, and have yielded state of the art performance in many classification problems, such as character recognition, object recognition and document categorization. However, little attention has been paid to the potential of deep learning for unsupervised clustering problems. In this paper, we propose a deep belief network with nonparametric clustering. As an unsupervised method, our model first leverages the advantages of deep learning for feature representation and dimension reduction. Then, it performs nonparametric clustering under a maximum margin framework -- a discriminative clustering model and can be trained online efficiently in the code space. Lastly model parameters are refined in the deep belief network. Thus, this model can learn features for clustering and infer model complexity in an unified framework. The experimental results show the advantage of our approach over competitive baselines.

14 pages, 6 figures

References in corpus (1)

• Natural Scales in Geographical Patterns

Cited by in corpus (13)

• Clustering with Deep Learning: Taxonomy and New Methods
• Joint Unsupervised Learning of Deep Representations and Image Clusters
• SpectralNet: Spectral Clustering using Deep Neural Networks
• Neural network-based clustering using pairwise constraints
• Data-Driven Fuzzy Modeling Using Deep Learning
• Deep Density-based Image Clustering
• Learning A Task-Specific Deep Architecture For Clustering
• Human-like Clustering with Deep Convolutional Neural Networks
• Topological Gradient-based Competitive Learning
• Node-By-Node Greedy Deep Learning for Interpretable Features
• Resolution and Relevance Trade-offs in Deep Learning
• A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs
• SA-Net: A deep spectral analysis network for image clustering