About the Workshop: Transfer learning is a machine learning method where a model developed for a task is reused as the starting point for a model on a second task. It is a popular approach in deep learning where pre-trained models are used as the starting point on computer vision and natural language processing tasks. This can be very important, given the vast compute and time resources required to develop neural network models on these problems and given the huge jumps in skill that these models can provide to related problems. In this part of the course we will examine various pre-existing models and techniques in transfer learning. Afternoon workshop hosted by Weights and Biases (WandB) WandB helps you track your machine learning experiments. Our mission is to build the best developer tools for deep learning. Use our tool to log hyperparameters and output metrics from your runs, manage hyperparameter sweeps, and compare results from different experiments with your team. https://www.wandb.com/ Click here to register.
About ComputeFest: Open to the public, ComputeFest is four days of advanced applied machine learning workshops led by IACS researchers, students, alumni, and industry presenters. Workshops are directed by IACS Lecturer and Scientific Director, Pavlos Protopapas.