Motivated by prior research which highlights inefficiencies in the feature representations learned by convolutional neural networks, we further introduce a novel inter-filter orthogonality metric for ranking filter importance for the purpose of RePr training, and demonstrate that this metric outperfo...
Neural network training is an optimization problem with non-convex objective function J: the minimization problem min𝛉𝐽(𝜃;𝒟train)minθJ(θ;Dtrain). During the training process, model parameters 𝛉θ are iteratively updated in order to reduce the cost J on the training data 𝒟train...