... augmenting 729 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 ... three worst cases in the test set
(remaining images).
Chapter 8
Application Examples in the...
... . . 106
8. 1 [a–d] Kinematic workspace of the TUM robot finger . . . . . 1 08
8.2 [a–e] Training and testing of the finger kinematics PSOM . . 110
Jörg A. Walter
Rapid Learning in Robotics
Robotics ... in Robotics 1
Die Deutsche Bibliothek — CIP Data
Walter, Jörg
Rapid Learning in Robotics / by Jörg Walter, 1st ed.
Göttingen: Cuvillier, 1996
Zugl.: Bielefeld, Univ., Dis...
... 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 “mixi...
... 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...
... training set, but is performing
badly on the indicated (cross-marked) position.
More training data: Over-fitting can be avoided when sufficient training
points are available, e.g. by learning on-line. ... cooperative learning in order to increase speed and ro-
bustness of learning, studied e.g. in Walter, Martinetz, and Schulten
(1991) and compared to the so-called Neural-Gas Network...
... 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-match in . In ... compared with one single interpolation 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 int...
... 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 ... mappings are smooth in certain domains, but non-
continuous in others. Then, different types of learning experts, like PSOMs,
Meta-PSOMs, LLMs, RBF and others can be chosen. The domain...
... 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. ... random lo-
cations (from within the range of the training set) seen in 10 different
1 38 “Mixture-of-Expertise” or “Investment Learning
camera setups, from within the square grid of th...
... Report
SFB360-TR-9 6-3 , Universität Bielefeld, D-33615 Bielefeld.
Walter, J., H. Ritter, and K. Schulten (1990, June). Non-linear predic-
tion with self-organizing maps. In Int. Joint Conf. on ... (1 989 ). Topology-
conserving maps for learning visuo-motor-coordination. Neural Net-
works 2, 159–1 68.
Rosenblatt, F. (1962). Principles of Neurodynamics. Spartan, New York.
Rumelhart, D...
... 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...