Deep Coding Network
Yuanqing Lin, Tong Zhang, Shenghuo Zhu B et al. · 2010
This paper proposes a principled extension of the traditional single-layer flat sparse coding scheme, where a two-layer coding scheme is derived based on theoretical analysis of nonlinear functional approximation that extends recent results for local coordinate coding. The two-layer approach can be easily generalized to deeper structures in a hierarchical multiple-layer manner. Empirically, it is shown that the deep coding approach yields improved performance in benchmark datasets. 1
Cited by 23 works.
Authors
References
- Reducing the Dimensionality of Data with Neural Networks
- Nonlinear Programming
- Emergence of simple-cell receptive field properties by learning a sparse code for natural images
- Linear spatial pyramid matching using sparse coding for image classification
- Efficient sparse coding algorithms
- Self-taught learning
- Sparse Feature Learning for Deep Belief Networks
- Learning Overcomplete Representations
- Nonlinear Learning using Local Coordinate Coding
- Supervised Dictionary Learning