Projects done in the course IT3030 - Deep Learning at NTNU.
- Project 1 contains a custom implementation of backpropagation in conjunction with a PyTorch-like API.
- Project 2 concerns using traditional autoencoders for unsupervised learning & classification on datasets such as CIFAR and Fashion-MNIST.
- Project 3 concerns variational autoencoders and generative adversarial networks on 3-channel (stacked) MNIST images. I also implemented the VEEGAN-algorithm [1].
[1] Akash, Srivastava et al. (2017). "VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning". In: Neural Information Processing Systems.