Skip to main content
placeholder image

Recognition of sequences of graphical patterns

Chapter


Abstract


  • Several real-world problems (e.g., in bioinformatics/proteomics, or in recognition of video sequences) can be described as classification tasks over sequences of structured data, i.e. sequences of graphs, in a natural way. This paper presents a novel machine that can learn and carry out decision-making over sequences of graphical data. The machine involves a hidden Markov model whose state-emission probabilities are defined over graphs. This is realized by combining recursive encoding networks and constrained radial basis function networks. A global optimization algorithm which regards to the machine as a unity (instead of a bare superposition of separate modules) is introduced, via gradient-ascent over the maximum-likelihood criterion within a Baum-Welch-like forward-backward procedure. To the best of our knowledge, this is the first machine learning approach capable of processing sequences of graphs without the need of a pre-processing step. Preliminary results are reported.

UOW Authors


  •   Trentin, Edmondo (external author)
  •   Zhang, Shujia (external author)
  •   Hagenbuchner, M.

Publication Date


  • 2010

Citation


  • Trentin, E., Zhang, S. & Hagenbuchner, M. (2010). Recognition of sequences of graphical patterns. Artificial Neural Networks in Pattern Recognition: 4th IAPR TC3 Workshop, ANNPR 2010, Cairo, Egypt, April 11-13, 2010. Proceedings (pp. 48-59). Germany: Springer Berlin Heidelberg.

Scopus Eid


  • 2-s2.0-77952325617

Book Title


  • Artificial Neural Networks in Pattern Recognition: 4th IAPR TC3 Workshop, ANNPR 2010, Cairo, Egypt, April 11-13, 2010. Proceedings

Start Page


  • 48

End Page


  • 59

Abstract


  • Several real-world problems (e.g., in bioinformatics/proteomics, or in recognition of video sequences) can be described as classification tasks over sequences of structured data, i.e. sequences of graphs, in a natural way. This paper presents a novel machine that can learn and carry out decision-making over sequences of graphical data. The machine involves a hidden Markov model whose state-emission probabilities are defined over graphs. This is realized by combining recursive encoding networks and constrained radial basis function networks. A global optimization algorithm which regards to the machine as a unity (instead of a bare superposition of separate modules) is introduced, via gradient-ascent over the maximum-likelihood criterion within a Baum-Welch-like forward-backward procedure. To the best of our knowledge, this is the first machine learning approach capable of processing sequences of graphs without the need of a pre-processing step. Preliminary results are reported.

UOW Authors


  •   Trentin, Edmondo (external author)
  •   Zhang, Shujia (external author)
  •   Hagenbuchner, M.

Publication Date


  • 2010

Citation


  • Trentin, E., Zhang, S. & Hagenbuchner, M. (2010). Recognition of sequences of graphical patterns. Artificial Neural Networks in Pattern Recognition: 4th IAPR TC3 Workshop, ANNPR 2010, Cairo, Egypt, April 11-13, 2010. Proceedings (pp. 48-59). Germany: Springer Berlin Heidelberg.

Scopus Eid


  • 2-s2.0-77952325617

Book Title


  • Artificial Neural Networks in Pattern Recognition: 4th IAPR TC3 Workshop, ANNPR 2010, Cairo, Egypt, April 11-13, 2010. Proceedings

Start Page


  • 48

End Page


  • 59