Exploring deep learning approaches with Fashion MNIST

This scientific project explores deep learning approaches using the Fashion MNIST dataset. The study compares various neural network variants, such as dense and convolutional networks (CNNs), and investigates different regularization techniques, including dropout, batch normalization, L2 regularization, as well as deep and wide architectures. Additionally, it compares the performance of different optimizers.

The full analysis can be accessed through the following link: Exploring DL approaches