David Bourget (Western Ontario)
David Chalmers (ANU, NYU)
Rafael De Clercq
Jack Alan Reynolds
Learn more about PhilPapers
Abstra,ct— This paper will discuss learning in hybrid models that goes beyond simple rule extraction from backpropagation networks. Although simple rule extraction has received a lot of research attention, to further develop hybrid learning models that include both symbolic and subsymbolic knowledge and that learn autonomously, it is necessary to study autonomous learning of both subsymbolic and symbolic knowledge in integrated architectures. This paper will describe knowledge extraction from neural reinforcement learning. It includes two approaches towards extracting plan knowledge: the extraction of explicit, symbolic rules from neural reinforcement learning, and the extraction of complete plans. This work points to the creation of a general framework for achieving the subsymbolic to symbolic transition in an integrated autonomous learning framework.
|Keywords||No keywords specified (fix it)|
|Categories||categorize this paper)|
|Through your library||Only published papers are available at libraries|
Similar books and articles
Christopher Cox, Christopher Manning & Pat Langley, Template Sampling for Leveraging Domain Knowledge in Information Extraction.
Ron Sun, Supplementing Neural Reinforcement Learning with Symbolic Methods Possibilities and Challenges.
Christian Lebiere & Dieter Wallach (1999). Implicit and Explicit Learning in a Hybrid Architecture of Cognition. Behavioral and Brain Sciences 22 (5):772-773.
Christopher Manning, Incorporating Non-Local Information Into Information Extraction Systems by Gibbs Sampling.
Added to index2009-06-13
Total downloads5 ( #176,133 of 1,011,230 )
Recent downloads (6 months)1 ( #64,700 of 1,011,230 )
How can I increase my downloads?