[EMNLP'20][Findings] Official Repository for the paper "Why and when should you pool? Analyzing Pooling in Recurrent Architectures."
Multilayer Perceptron GAN, and two Convolutional Neural Network GANs for MNIST and CIFAR.
Adaptive-saturated RNN: Remember more with less instability
Code repository for my CSU master's research on dead ReLU's
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.
Add a description, image, and links to the vanishing-gradient topic page so that developers can more easily learn about it.
To associate your repository with the vanishing-gradient topic, visit your repo's landing page and select "manage topics."