Rapid Learning in Robotics - Jorg Walter Part 9 docx

... Application Examples in the Robotics Domain 2. What is the in uence of standard and Chebyshev-spaced sampling of training points inside their working interval? When the data val- ues (here 3 per ... engaged at any time. 9. 2 “Investment Learning or “Mixture-of-Expertise” Architecture 127 9. 2 “Investment Learning or “Mixture-of-Expertise” Architecture Here, we approach a solution in...

Ngày tải lên: 10/08/2014, 02:20

... when a bell J. Walter Rapid Learning in Robotics 1 Die Deutsche Bibliothek — CIP Data Walter, Jörg Rapid Learning in Robotics / by Jörg Walter, 1st ed. Göttingen: Cuvillier, 199 6 Zugl.: Bielefeld, ... 123 9 “Mixture-of-Expertise” or “Investment Learning 125 9. 1 Context dependent “skills” . . . . . . . . . . . . . . . . . . . 125 9. 2 “Investment Learning or “Mixture-...

Ngày tải lên: 10/08/2014, 02:20

... comply to extra constraints. Chapter 9 turns to the next higher level of one-shot learning. Here the learning of prototypical mappings is used to rapidly adapt a learning sys- tem to new context ... investment learning stage, since effort is invested, to train the system for the second, the one-shot learning phase. Observing the context, the system can now adapt most rapidly by “mi...

Ngày tải lên: 10/08/2014, 02:20

... training examples in a stochastic sequence. Iterative learning is usually more efficient, particularly w.r.t. memory requirements. Off-line versus On-line Learning and Interferences: Off-line learning ... by the so-called “catastrophic inter- ference”, see “on-line learning below. Batch versus Incremental Learning: Calculating the network weight up- dates under consideration of all t...

Ngày tải lên: 10/08/2014, 02:20

... cooperative learning in order to increase speed and ro- bustness of learning, studied e.g. in Walter, Martinetz, and Schulten ( 199 1) and compared to the so-called Neural-Gas Network in Walter ( 199 1) ... 198 9; Walter and Schulten 199 3). In time-series prediction it was introduced in conjunction with the SOM (Walter, Ritter, and Schulten 199 0) and later with the Neural-...

Ngày tải lên: 10/08/2014, 02:20

... polynomial in a selected node sub-grid, as described. For the bi-cubic, so-called tensor-product spline is usually com- puted by row-wise spline interpolation and a column spline over the row interpolation ... training data. The beginning in- folding of the map, e.g. seen at the lower left corner in Fig. 5.8 demonstrates further that shows multiple solutions (Eq. 4.4) for finding a best-m...

Ngày tải lên: 10/08/2014, 02:20

... augmenting 7 29 joint angle vectors on a rectangular 3 3 3 3 3 3 grid in joint angle space with the missing – 112 Application Examples in the Robotics Domain -4 0 -3 0 -2 0 -1 0 0 10 20 30 40 -4 0 -3 0 -2 0 -1 0 0 10 20 3 0 90 100 110 120 130 140 150 160 x y z r ... inputs. All remaining results are obtained using only four (non-coplanar) points as inputs. 104...

Ngày tải lên: 10/08/2014, 02:20

... efficient learning modules for the continuous and smooth mapping domain, the “mixture-of-expert” scheme is superior in managing mapping domains which require non-continuous or non-smooth interfaces. ... retina coordinates (2D in each camera) . Thus the training vectors for the construction of the T-PSOM are the tuples . 9. 3 Examples 137 In the investing pre-training phase, nine mappi...

Ngày tải lên: 10/08/2014, 02:20

... Martinetz, and K. J. Schulten ( 198 9). Topology- conserving maps for learning visuo-motor-coordination. Neural Net- works 2, 1 59 168. Rosenblatt, F. ( 196 2). Principles of Neurodynamics. Spartan, ... De- partment der Technische Universität München. Walter, J. ( 199 6). SORMA: Interoperating distributed robotics hardware. In Proc. Int. Conf. on Robotics and Automation (ICRA -9 7 ),...

Ngày tải lên: 10/08/2014, 02:20

... cooperative learning in order to increase speed and ro- bustness of learning, studied e.g. in Walter, Martinetz, and Schulten ( 199 1) and compared to the so-called Neural-Gas Network in Walter ( 199 1) ... training examples in a stochastic sequence. Iterative learning is usually more efficient, particularly w.r.t. memory requirements. Off-line versus On-line Learning and Int...

Ngày tải lên: 27/06/2014, 18:20