Investment Learning with Hierarchical PSOMs
نویسندگان
چکیده
We propose a hierarchical scheme for rapid learning of context dependent "skills" that is based on the recently introduced "Parameterized SelfOrganizing Map" ("PSOM"). The underlying idea is to first invest some learning effort to specialize the system into a rapid learner for a more restricted range of contexts. The specialization is carried out by a prior "investment learning stage", during which the system acquires a set of basis mappings or "skills" for a set of prototypical contexts. Adaptation of a "skill" to a new context can then be achieved by interpolating in the space of the basis mappings and thus can be extremely rapid. We demonstrate the potential of this approach for the task of a 3D visuomotor map for a Puma robot and two cameras. This includes the forward and backward robot kinematics in 3D end effector coordinates, the 2D+2D retina coordinates and also the 6D joint angles. After the investment phase the transformation can be learned for a new camera set-up with a single observation.
منابع مشابه
Rapid learning with parametrized self-organizing maps
The construction of computer vision and robot control algorithms from training data is a challenging application for artiicial neural networks. However, many practical applications require an approach that is workable with a small number of data examples. In this contribution, we describe results on the use of \Parametrized Self-organizing Maps" (\PSOMs") with this goal in mind. We report resul...
متن کاملAssociative Completion and Investment Learning Using PSOMs
We describe a hierarchical scheme for rapid adaptation of context dependent \skills". The underlying idea is to rst invest some learning eeort to specialize the learning system to become a rapid learner for a restricted range of contexts. This is achieved by constructing a \Meta-mapping" that replaces an slow and iterative context adaptation by a \one-shot adaptation", which is a context-depend...
متن کاملInvestment Learning with Hierarchical Psom
The recently introduced \Parameterized Self-Organizing Maps" (\PSOM") shows excellent function mapping capabilities after learning of a remarkable small set of training data. This is a very important feature in elds where the acquisition of training data is costly, for example in robotics. As a rst demonstration, we compare results for the task of kinematic mapping of a 3-DOF robot nger, obtain...
متن کاملLocal PSOMs and Chebyshev PSOMs Improving the Parametrised Self-Organizing Maps1
We report on two new improvements for the “Parameterised Self-Organizing Map” (PSOM). Both achieve a significant increase in mapping accuracy and computational efficiency. For a growing number of training points the use of higher order polynomials to construct the PSOM “mapping manifold” in [7] can suffer from the increasing tendency to oscillate between the support points. We propose here to c...
متن کاملQuantifying Investment in Language Learning: Model and Questionnaire Development and Validation in the Iranian Context
The present exploratory study aimed to provide a more tangible and comprehensive picture of the construct of investment in language learning through investigating the issue from a quantitative perspective. To this end, the present researchers followed three main phases. First, a hypothesized model of investment in language learning with six components was developed for the Iranian English as a ...
متن کامل