Neural network node output distributions are nonlinear projections along hypersurfaces via Radon transforms, yielding geometric interpretations for nonlinearity, pooling, activations, and adversarial examples.
Rectified linear units improve restricted boltz- mann machines,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2019 4verdicts
UNVERDICTED 4representative citing papers
The paper shows that multiple-identity image attacks succeed due to modest angular separation between matching (~90°) and non-matching (40-60°) face representations, with image morphing and representation inversion realizing effective attacks that transfer across comparators.
The paper derives intercept probability for cooperative NOMA SWIPT with eavesdropper and shows deep learning optimization of power allocation outperforms iterative search.
A CNN plus LSTM model on 64 ms raw audio segments from SVD achieves 68% test accuracy for voice pathology detection, comparable to earlier work with different features.
citing papers explorer
-
Neural Networks, Hypersurfaces, and Radon Transforms
Neural network node output distributions are nonlinear projections along hypersurfaces via Radon transforms, yielding geometric interpretations for nonlinearity, pooling, activations, and adversarial examples.
-
Multiple-Identity Image Attacks Against Face-based Identity Verification
The paper shows that multiple-identity image attacks succeed due to modest angular separation between matching (~90°) and non-matching (40-60°) face representations, with image morphing and representation inversion realizing effective attacks that transfer across comparators.
-
Secrecy Analysis and Learning-based Optimization of Cooperative NOMA SWIPT Systems
The paper derives intercept probability for cooperative NOMA SWIPT with eavesdropper and shows deep learning optimization of power allocation outperforms iterative search.
-
Voice Pathology Detection Using Deep Learning: a Preliminary Study
A CNN plus LSTM model on 64 ms raw audio segments from SVD achieves 68% test accuracy for voice pathology detection, comparable to earlier work with different features.