Zusammenfassung
Implicit deep learning prediction rules generalize the recursive rules of
feedforward neural networks. Such rules are based on the solution of a
fixed-point equation involving a single vector of hidden features, which is
thus only implicitly defined. The implicit framework greatly simplifies the
notation of deep learning, and opens up many new possibilities, in terms of
novel architectures and algorithms, robustness analysis and design,
interpretability, sparsity, and network architecture optimization.
Nutzer