Inductive Bias of Gradient Descent for Exponentially Weight Normalized Smooth Homogeneous Neural Nets.
Depen MorwaniHarish G. RamaswamyPublished in: CoRR (2020)
Keyphrases
- neural nets
- inductive bias
- machine learning
- learning tasks
- hypothesis space
- inductive learning
- feed forward
- neural network
- pac learning
- supervised learning
- back propagation
- multitask learning
- training examples
- prior knowledge
- domain knowledge
- artificial neural networks
- training set
- active learning
- multi task
- domain theory
- objective function
- uniform distribution
- support vector
- similarity measure
- sample selection
- learning theory