Rupesh K Srivastava

continual learning (1) catastrophic forgetting (1) feature learning (1) deep learning (1) gradient descent (1) local competition (1) multilayer neural networks (1) backprop training (1) deep neural network (1) information flow (1) deep network (1) network depth (1) gating mechanism (1) highway network (1) gradient-based learning (1) neural network (1) adaptive gating (1) gating unit (1) layered architecture (1) information highway (1)