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 delves into the fundamentals of Convolutional Neural Networks (CNNs), explaining their architecture and key concepts such as weight sharing, translation invariance, and global context importance. The instructor discusses the implementation of CNNs for image processing, emphasizing the significance of filters, padding, and pooling. The lecture also covers practical aspects like multiband filters, color composition analysis, and classifier design. By the end, students gain insights into CNN design principles, learning mechanisms, and tricks for efficient training.