Neural methods for non-standard data

Standard pattern recognition provides effective and noise-tolerant tools for machine learning tasks; however, most approaches only deal with real vectors of a finite and fixed dimensionality. In this tutorial paper, we give an overview about extensions of pattern recognition towards non-standard data which are not contained in a finite dimensional space, such as strings, sequences, trees, graphs, or functions. Two major directions can be distinguished in the neural networks literature: models can be based on a similarity measure adapted to non-standard data, including kernel methods for structures as a very prominent approach, but also alternative metric based algorithms and functional networks; alternatively, non-standard data can be processed recursively within supervised and unsupervised recurrent and recursive networks and fully recurrent systems.

• Type: Conference
• Year: 2004
• Where: ESANN
• Authors: Barbara Hammer, Brijnesh J. Jain
• Keywords: ESANN 2004, ESANN 2007, Non-standard Data, Pattern Recognition, Standard Pattern Recognition