Implicit Deep Learning
Laurent El Ghaoui, Fangda Gu, Bertrand Travacca, Armin Askari, Alicia Y. Tsai
Abstract
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.
Topics & Concepts
InterpretabilityDeep learningComputer scienceNotationArtificial intelligenceRobustness (evolution)Feed forwardArtificial neural networkTheoretical computer scienceMachine learningAlgorithmMathematicsArithmeticGeneBiochemistryControl engineeringChemistryEngineeringAdversarial Robustness in Machine LearningModel Reduction and Neural NetworksNeural Networks and Applications