A new perspective for understanding generalization gap of deep neural networks trained with large batch sizes
Oyebade K. Oyedotun, Konstantinos Papadopoulos, Djamila Aouada
Topics & Concepts
MNIST databaseGeneralizationComputer scienceStochastic gradient descentArtificial neural networkArtificial intelligenceDeep learningRank (graph theory)Machine learningAlgorithmMathematicsMathematical analysisCombinatoricsAdvanced Neural Network ApplicationsMachine Learning and ELMDomain Adaptation and Few-Shot Learning