Transfer Learning and Intelligence: an Argument and Approach
08:18
-
1 year ago
In the AGI-08 presentation on Transfer Learning and Intelligence, Matthew Taylor argues that in order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. The conference paper by the speaker, Gregory Kuhlmann, and Peter Stone explains that classical machine learning techniques have had many significant empirical successes, but large real-world problems that are of interest to generally intelligent agents require learning much faster (with much less training experience) than is currently possible. The paper presents transfer learning, where knowledge from a learned task can be used to significantly speed up learning in a novel task, as the key to achieving the learning capabilities necessary for general intelligence.In the AGI-08 presentation on Transfer Learning and Intelligence, Matthew Taylor argues that in order to claim fully general intelligence in...all »In the AGI-08 presentation on Transfer Learning and Intelligence, Matthew Taylor argues that in order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. The conference paper by the speaker, Gregory Kuhlmann, and Peter Stone explains that classical machine learning techniques have had many significant empirical successes, but large real-world problems that are of interest to generally intelligent agents require learning much faster (with much less training experience) than is currently possible. The paper presents transfer learning, where knowledge from a learned task can be used to significantly speed up learning in a novel task, as the key to achieving the learning capabilities necessary for general intelligence.«
Download is starting. Save file to your computer. If the download does not start automatically, right-click this link and choose "Save As". How to get videos onto the iPod or PSP.
