Rapid Learning in Robotics - Jorg Walter Part 11 pps

... 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 ... SFB360-TR-9 6-4 , TF-AG-NI, Universität Bielefeld, D-33615 Bielefeld. Walter, J. and H. Ritter (1996d). Rapid learning with parametrized self- organizing maps. Neurocomputing 12, 131–15...

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 “mixi...

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

... 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 138 “Mixture-of-Expertise” or “Investment Learning camera setups, from within the square grid of the...

Ngày tải lên: 10/08/2014, 02:20

... 106 8.1 [a–d] Kinematic workspace of the TUM robot finger . . . . . 108 8.2 [a–e] Training and testing of the finger kinematics PSOM . . 110 Jörg A. Walter Rapid Learning in Robotics Robotics deals ... efficient mapping which solves the de- sired learning task? Chapter 3 explains Kohonen's “Self-Organizing Map” procedure and techniques to improve the learning of continuous,...

Ngày tải lên: 10/08/2014, 02:20

... 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...

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 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 ... Kinematics Mapping 113 -4 0 -3 0 -2 0 -1 0 0 10 20 30 40 -4 0 -3 0 -2 0...

Ngày tải lên: 10/08/2014, 02:20

... 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...

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: 27/06/2014, 18:20