Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture introduces the Pytorch framework by exploring the MNIST dataset for handwritten digit recognition and the Digits dataset. It covers loading datasets, creating dataloaders, visualizing data, training a perceptron, and testing neural networks. Additionally, it delves into the concepts of normalization, transformation, and the impact of dataset size on training performance.