Loading Deep Networks Is Hard: The Pyramidal Case

Authors:
David Windisch
Affiliations:
Bahnplatz 5, A-2371 Hinterbruehl, Austria
Venue:
Neural Computation
Year:
2005

Citing 9
Cited 0

Neural network design and the complexity of learning

Neural network design and the complexity of learning
Original Contribution: Training a 3-node neural network is NP-complete

Neural Networks
Loading deep networks is hard

Neural Computation
Robust trainability of single neurons

Journal of Computer and System Sciences
Back-propagation is not efficient

Neural Networks
On the infeasibility of training neural networks with small squared errors

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Computers and Intractability: A Guide to the Theory of NP-Completeness

Computers and Intractability: A Guide to the Theory of NP-Completeness
Hardness results for neural network approximation problems

Theoretical Computer Science
Training a single sigmoidal neuron is hard

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The question of whether it is possible to load deep neural network architectures efficiently is examined by considering the class of pyramidal architectures. This class allows only a low interaction of the nodes. Still, the loading problem is found to be NP-complete. This provides evidence that depth alone is a factor accounting for loading hardness.