2 papers
cs.CV2021
A Sparse Coding Interpretation of Neural Networks and Theoretical Implications
Joshua Bowren
Neural networks, specifically deep convolutional neural networks, have achieved unprecedented performance in various computer vision tasks, but the rationale for the computations a…
cs.CV2021
Inference via Sparse Coding in a Hierarchical Vision Model
Joshua Bowren, Luis Sanchez-Giraldo, Odelia Schwartz
Sparse coding has been incorporated in models of the visual cortex for its computational advantages and connection to biology. But how the level of sparsity contributes to performa…