Neural network node output distributions are nonlinear projections along hypersurfaces via Radon transforms, yielding geometric interpretations for nonlinearity, pooling, activations, and adversarial examples.
Approximation by superpositions of a sigmoidal function
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Supervised and reinforcement learning predict LTE control information to enable more device sleep states, with reported energy savings up to 17%.
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.
-
Adaptive Predictive Power Management for Mobile LTE Devices
Supervised and reinforcement learning predict LTE control information to enable more device sleep states, with reported energy savings up to 17%.