Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions.
Junru WuYue WangZhenyu WuZhangyang WangAshok VeeraraghavanYingyan LinPublished in: CoRR (2018)
Keyphrases
- clustering algorithm
- k means
- deep architectures
- data clustering
- hierarchical clustering
- unsupervised clustering
- cluster analysis
- cluster centers
- deep learning
- clustering method
- spectral clustering
- training set
- parameter space
- learning algorithm
- hierarchical agglomerative clustering
- training phase
- training process
- np complete
- supervised learning
- data points
- np hard