Evolving lifted data vectors under a chaotic dynamical system before softmax classification accelerates training and improves accuracy over standard and lifted-only baselines on perturbed orthogonal vectors.
Deep learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
New l2- and l1-based greedy algorithms derived from a solution characterization outperform classical OMP and basis pursuit on synthetic and image data.
citing papers explorer
-
Enhancing classification accuracy through chaos
Evolving lifted data vectors under a chaotic dynamical system before softmax classification accelerates training and improves accuracy over standard and lifted-only baselines on perturbed orthogonal vectors.
-
On A Class of Greedy Sparse Recovery Algorithms
New l2- and l1-based greedy algorithms derived from a solution characterization outperform classical OMP and basis pursuit on synthetic and image data.