Header logo is


2004


no image
Grain boundary phase transitions and their influence on properties of polycrystals

Straumal, B., Baretzky, B.

{Interface Science}, 12(2-3):147-155, 2004 (article)

mms

[BibTex]

2004


[BibTex]


no image
Swift heavy ion induced modification of Si/C60 multilayers

Srivastava, S. K., Kabiraj, D., Schattat, B., Carstanjen, H. D., Avasthi, D. K.

{Nuclear Instruments and Methods in Physics Research B}, 219 - 220, pages: 815-819, 2004 (article)

mms

[BibTex]

[BibTex]


no image
Static displacements of Pd in the solid solution PdBy (0\textlessy\textless0.2) as determined by neutron diffraction

Berger, T. G., Leineweber, A., Mittemeijer, E. J., Fischer, P.

{Physica Status Solidi (A)}, 201, pages: 1484-1492, 2004 (article)

mms

[BibTex]

[BibTex]


no image
X-MCD magnetometry of CMR perovskites La0.67-yREyCa0.33MnO3

Sikora, M., Kapusta, C., Zajac, D., Tokarz, W., Oates, C. J., Borowiec, M., Rybicki, D., Goering, E. J., Fischer, P., Schütz, G., De Teresa, J. M., Ibarra, M. R.

{Journal of Magnetism and Magnetic Materials}, 272-276, pages: 2148-2150, 2004 (article)

mms

[BibTex]

[BibTex]


no image
Critical thicknesses of domain formations in cubic particles and thin films

Kronmüller, H., Goll, D., Hertel, R., Schütz, G.

{Physica B}, 343(1-4):229-235, 2004 (article)

mms

[BibTex]

[BibTex]

1995


no image
Memory-based neural networks for robot learning

Atkeson, C. G., Schaal, S.

Neurocomputing, 9, pages: 1-27, 1995, clmc (article)

Abstract
This paper explores a memory-based approach to robot learning, using memory-based neural networks to learn models of the task to be performed. Steinbuch and Taylor presented neural network designs to explicitly store training data and do nearest neighbor lookup in the early 1960s. In this paper their nearest neighbor network is augmented with a local model network, which fits a local model to a set of nearest neighbors. This network design is equivalent to a statistical approach known as locally weighted regression, in which a local model is formed to answer each query, using a weighted regression in which nearby points (similar experiences) are weighted more than distant points (less relevant experiences). We illustrate this approach by describing how it has been used to enable a robot to learn a difficult juggling task. Keywords: memory-based, robot learning, locally weighted regression, nearest neighbor, local models.

am

link (url) [BibTex]

1995


link (url) [BibTex]