👵Classic Networks
Last updated
Last updated
Network | First Usage |
LeNet-5 | Hand written digit classification |
AlexNet | ImageNet Dataset |
VGG-16 | ImageNet Dataset |
LeNet-5 is a very simple network - By modern standards -. It only has 7 layers;
among which there are 3 convolutional layers (C1, C3 and C5)
2 sub-sampling (pooling) layers (S2 and S4)
1 fully connected layer (F6)
Output layer
Too similar to LeNet-5
It has more filters per layer
It uses ReLU instead of tanh
SGD with momentum
Uses dropout instead of regularaization
It is painfully slow to train (It has 138 million parameters 🙄)
