Pages that link to "Item:Q2117333"

The following pages link to Neural network identifiability for a family of sigmoidal nonlinearities (Q2117333):

Displaying 8 items.

• Reconstructing a neural net from its output (Q1344572) (← links)
• Nonlinearity creates linear independence (Q1923888) (← links)
• Stable recovery of entangled weights: towards robust identification of deep neural networks from minimal samples (Q2105108) (← links)
• Robust and resource-efficient identification of two hidden layer neural networks (Q2117339) (← links)
• Metric entropy limits on recurrent neural network learning of linear dynamical systems (Q2134114) (← links)
• Affine symmetries and neural network identifiability (Q2214101) (← links)
• A note on the identifiability of the conditional expectation for the mixtures of neural networks (Q2483449) (← links)
• Approximation error for neural network operators by an averaged modulus of smoothness (Q6093307) (← links)