Abtdmet-Constrained motion control of robotic manipulators represents an important control task in many industrial applications. In this paper, a learning control problem is solved for simultaneous motion and force tracking of a robotic manipulator whose end-effector is in contact with the constrain
Robust Learning Aided by Context
β Scribed by John Case; Sanjay Jain; Matthias Ott; Arun Sharma; Frank Stephan
- Publisher
- Elsevier Science
- Year
- 2000
- Tongue
- English
- Weight
- 207 KB
- Volume
- 60
- Category
- Article
- ISSN
- 0022-0000
No coin nor oath required. For personal study only.
β¦ Synopsis
Empirical studies of multitask learning provide some evidence that the performance of a learning system on its intended targets improves by presenting to the learning system related tasks, also called contexts, as additional input. Angluin, Gasarch, and Smith, as well as Kinber, Smith, Velauthapillai, and Wiehagen, have provided mathematical justification for this phenomenon in the inductive inference framework. However, their proofs rely heavily on selfreferential coding tricks; that is, they directly code the solution of the learning problem into the context. Fulk has shown that for the Ex-and Bc-anomaly
π SIMILAR VOLUMES
## Abstract Instead of the traditional view of learning as acquiring cognitive knowledge or data, the author argues for a broader notion of knowledge that includes emotions, values, intuition, and creativity.