Abstract | ||
---|---|---|
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. |
Year | Venue | Field |
---|---|---|
2010 | NIPS | Linear network coding,Nonlinear system,Neural coding,Computer science,Theoretical computer science,Coding (social sciences),Artificial intelligence,Functional approximation,Machine learning |
DocType | Citations | PageRank |
Conference | 5 | 0.86 |
References | Authors | |
9 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lin, Yuanqing | 1 | 1143 | 59.04 |
Zhang, Tong | 2 | 7126 | 611.43 |
Zhu, Shenghuo | 3 | 2996 | 167.68 |
Yu, Kai | 4 | 4799 | 255.21 |