Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Jun 201819922001200920182026
1 result for “Stripe-sparsity”
Towards an understanding of CNNs: analysing the recovery of activation pathways via Deep Convolutional Sparse Codingcs.LG

D-CSC framework reveals how ReLU activation functions recover activation paths in neural networks.

problem Understanding how ReLU activation functions recover activation paths in neural networks.
method Deep Convolutional Sparse Coding (D-CSC) framework, omitting dictionary learning, to analyze activation paths.
result Uniform guarantees for recovery of true activation paths with high probability for greater activation densities.
Deep Convolutional Sparse CodingReLU activationActivation recoveryDeep Convolutional Neural NetworksStripe-sparsity
2018-06-26abs ↗pdf ↗