Self-Organizing Maps for Supervision in Robot Pick-And-Place Operations
A scheme for supervised learning based on multiple self-organizing maps (SOMs) is presented, and its application to robotic tasks, namely pick-and-place operations, is outlined. The advantage of this multiple organization is that the learning method is simplified because the problem is divided into several SOMs, which are trained in the standard unsupervised way. The resulting network preserves the SOM properties like dimensionality reduction and cluster formation, and its classification performance is comparable to other supervised methods like backpropagation networks.
KeywordsSupervise Learning Supervise Method Supervise Learning Method Bayesian Classification Robotic Task
Unable to display preview. Download preview PDF.
- 2.Cervera, E., del Pobil, A.P., Marta, E., Serna, M.A.: Unsupervised Learning for Error Detection in Task Planning, Computer Science Dept. Tech Report, Jaume I University, 1994.Google Scholar
- 4.Hertz, J., Krogh, A., Palmer, R.G.: Introduction to the Theory of Neural Computation. Addison-Wesley 1991.Google Scholar
- 5.Kurimo, K.: Proc. IEEE Workshop on Neural Networks for Signal Processing, 362, 1994.Google Scholar
- 7.Kohonen, T., Barna, G., Chrisley, R.: Proceedings of the IEEE International Conference on Neural Networks, San Diego, 1, 61, 1988.Google Scholar