Machine Learning Practical - Coursework 2: Analysing problems with the VGG deep neural network architectures (with 8 and 38 hidden layers) on the CIFAR100 dataset by monitoring gradient flow during training. And exploring solutions using batch normalization and residual connections.
vgg batch-normalization convolutional-neural-networks cifar100 vanishing-gradient residual-connections exploding-gradient
-
Updated
Dec 9, 2021 - Python