Timezone: »

 
Poster
The Sparse Manifold Transform
Yubei Chen · Dylan Paiton · Bruno Olshausen

Thu Dec 06 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #108
in Thu Poster Session B »

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.

Keywords: Unsupervised Learning · Nonlinear Dimensionality Reduction and Manifold Learning · Sparsity and Compressed Sensing · Sparse Coding and Dimensionality Expansion
[ Paper] 

Author Information

Yubei Chen (EECS & Mathematics UC Berkeley)
Dylan Paiton (University of California, Berkeley)
Bruno Olshausen (Redwood Center/UC Berkeley)

More from the Same Authors