- Transfer Learning Across Tasks: From Classification to Semantic Segmentation, Workshop, Harvard ComputeFest, 2020. Workshop material. Prepared by Vincent Casser, Camilo Fosco, Robbert Struyven.
Abstract
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 computational 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 program we will examine various pre-existing models and techniques in transfer learning.