Abstract
The construction of a feed-forward controller frequently requires the estimation of an inverse function. Two possible methods to achieve this are: (i) learning the best estimated inverse (BEI), a method that is sometimes referred to as direct inverse learning and (ii) learning the inverse of the best estimator (IBE), a method that is sometimes referred to as indirect inverse learning. We analyze a general control problem, in the presence of noise, and show analytically that these two methods are asymptotically significantly different, even for simple linear non-redundant systems. We further demonstrate that the IBE method is typically superior for control purposes.
Original language | English |
---|---|
Pages (from-to) | 1153-1159 |
Number of pages | 7 |
Journal | Neural Networks |
Volume | 14 |
Issue number | 9 |
DOIs | |
State | Published - 11 Oct 2001 |
Externally published | Yes |
Keywords
- Adaptive control
- Direct inverse learning
- Feedforward systems
- Indirect inverse learning
- Motor control
- Neural networks for control
- Neurocontrollers
- inverse control
ASJC Scopus subject areas
- Cognitive Neuroscience
- Artificial Intelligence