2026-09-18T16:08:57Zhttps://digital.lib.washington.edu/server/oai/request

oai:digital.lib.washington.edu:1773/459312026-02-16T02:06:37Zcom_1773_4888col_1773_4909

Farhadi, Ali Fox, Dieter Gordon, Daniel 2020-08-14T03:28:36Z 2020-08-14T03:28:36Z 2020-08-14 2020 Gordon_washington_0250E_21404.pdf http://hdl.handle.net/1773/45931 Thesis (Ph.D.)--University of Washington, 2020 When we are babies, we learn how to see by watching how the world changes and by interacting with it. Can we use these same signals to train vision models? In this thesis, we outline several works which use these paradigms as a basis for learning algorithms. First, we explore learning by watching in which video data is directly used to learn about the visual world. Second, we tackle multiple challenging tasks in embodied environments in which agents learn by interacting with their surroundings. application/pdf en_US CC BY-SA Computer Vision Deep Learning Machine Learning Computer science Robotics Computer science and engineering Learning by Watching and Learning by Doing Thesis Open Access open.access