Abstract | ||
---|---|---|
We present a signal representation framework called the sparse manifold transform that combines key ideas from sparse coding, manifold learning, and slow feature analysis. It turns non-linear transformations in the primary sensory signal space into linear interpolations in a representational embedding space while maintaining approximate invertibility. The sparse manifold transform is an unsupervised and generative framework that explicitly and simultaneously models the sparse discreteness and low-dimensional manifold structure found in natural scenes. When stacked, it also models hierarchical composition. We provide a theoretical description of the transform and demonstrate properties of the learned representation on both synthetic data and natural videos. |
Year | Venue | Keywords |
---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | synthetic data,sparse coding,manifold learning,key ideas,the sparse manifold transform |
DocType | Volume | ISSN |
Conference | 31 | 1049-5258 |
Citations | PageRank | References |
0 | 0.34 | 19 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yubei Chen | 1 | 16 | 2.74 |
Dylan M. Paiton | 2 | 2 | 1.40 |
Bruno A. Olshausen | 3 | 493 | 66.79 |