We introduce DropConnect, a generalization of Dropout (Hinton et al., 2012), for regularizing large fully-connected layers within neural networks. When training with Dropout, a randomly selected subset of activations are set to zero within each layer... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Image Classification MNIST DropConnect Percentage error 0.21 # 4

Methods used in the Paper