Perception-action (P-A) learning is an approach to cognitive system building that seeks to reduce the complexity associated with conventional environment-representation/action-planning approaches. Instead, actions are directly mapped onto the perceptual transitions that they bring about, eliminating the need for intermediate representation and significantly reducing training requirements. We here set out a very general learning framework for cognitive systems in which online learning of the P-A mapping may be conducted within a symbolic processing context, so that complex contextual reasoning can influence the P-A mapping. In utilizing a variational calculus approach to define a suitable objective function, the P-A mapping can be treated as an online learning problem via gradient descent using partial derivatives. Our central theoretical result is to demonstrate top-down modulation of low-level perceptual confidences via the Jacobian of the higher levels of a subsumptive P-A hierarchy. Thus, the separation of the Jacobian as a multiplying factor between levels within the objective function naturally enables the integration of abstract symbolic manipulation in the form of fuzzy deductive logic into the P-A mapping learning. We experimentally demonstrate that the resulting framework achieves significantly better accuracy than using P-A learning without top-down modulation. We also demonstrate that it permits novel forms of context-dependent multilevel P-A mapping, applying the mechanism in the context of an intelligent driver assistance system. / DIPLECS / GARNICS / CUAS
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:liu-85688 |
| Date | January 2013 |
| Creators | Windridge, David, Felsberg, Michael, Shaukat, Affan |
| Publisher | Linköpings universitet, Datorseende, Linköpings universitet, Tekniska högskolan, University of Surrey, Guildford, U.K., University of Surrey, Guildford, U.K., IEEE |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Article in journal, info:eu-repo/semantics/article, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | IEEE transactions on systems, man and cybernetics. Part B. Cybernetics, 1083-4419, 2013, 43:1, s. 155-169 |
Page generated in 0.0027 seconds