Co-Classification with Output Space Regularization

Structured learning algorithms usually require inference during the training procedure. Due to their exponential size of output space, the parameter update is performed only on a relatively small collection built from the ?best? structures. The k-best MIRA is an example of an online algorithm which seeks optimal parameters by making updates on k structures with the highest score at a time. Following the idea of using k-best structures during the learning process, in this paper we introduce four new k-best extensions of max-margin structured algorithms. We discuss their properties and connection, and evaluate all algorithms on two sequence labeling problems, the shallow parsing and named entity recognition. The experiments show how the proposed algorithms are affected by the changes of k in terms of the F-measure and computational time, and that the proposed algorithms can improve results in comparison to the single best case. Moreover, the restriction to the single best case produces a comparison of the existing algorithms.

Download Full-text

Evaluation of the capability of multilayer perceptron using total curvature of hypersurface: in the output-space

Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan) ◽

10.1109/ijcnn.1993.716816 ◽

2005 ◽

Author(s):

T. Matsumoto ◽

J. Toriwaki ◽

T. Yonekura

Keyword(s):

Multilayer Perceptron ◽

Total Curvature ◽

Output Space

Download Full-text

Experimental force reconstruction on plates of arbitrary shape using neural networks

INTER-NOISE and NOISE-CON Congress and Conference Proceedings ◽

10.3397/in-2021-2397 ◽

2021 ◽

Vol 263 (3) ◽

pp. 3407-3416

Author(s):

Tyler Dare

Keyword(s):

Neural Network ◽

Neural Networks ◽

Inverse Problem ◽

Artificial Neural Network ◽

Rectangular Plate ◽

Arbitrary Shape ◽

Impulsive Force ◽

Force Reconstruction ◽

Output Space ◽

Arbitrary Shapes

Measuring the forces that excite a structure into vibration is an important tool in modeling the system and investigating ways to reduce the vibration. However, determining the forces that have been applied to a vibrating structure can be a challenging inverse problem, even when the structure is instrumented with a large number of sensors. Previously, an artificial neural network was developed to identify the location of an impulsive force on a rectangular plate. In this research, the techniques were extended to plates of arbitrary shape. The principal challenge of arbitrary shapes is that some combinations of network outputs (x- and y-coordinates) are invalid. For example, for a plate with a hole in the middle, the network should not output that the force was applied in the center of the hole. Different methods of accommodating arbitrary shapes were investigated, including output space quantization and selecting the closest valid region.

Download Full-text