In this course we will explore the basics of Deep Learning and learn how neural networks can be trained and deployed for several applications. The main focus is on hands-on practice with programming tasks rather than studying the theoretical foundations of Machine Learning. The participants will first learn how to implement a neural network from scratch using a toy task before several important aspects of Deep Learning (optimisation, normalisation, architecture design, etc.) are applied to a computer vision task. The remainder of this course will focus more on the application level where models for time-series prediction and sequence-to-sequence learning are implemented. We will use Python and PyTorch for developing the models and each participant is assigned to an NVIDIA RTX 2080 TI for training.
The event is currently planned for presence only. In case there's high demand for hybrid mode, we will try to make this possible.
