Peter Súkeník

neural collapse (2) gradient descent (2) deep neural network (2) binary classification (1) knowledge distillation (1) multi-class classification (1) singular value decomposition (1) convolutional neural network (1) global optimum (1) unconstrained features model (1) neural network (1) low-data regime (1) fully-connected layer (1) deep neural collapse (1) gradient outer product (1) active learning (1) low-rank bia (1) representation learning (1) feature learning (1)