Recognition of Sequences of Graphical Patterns
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.
KeywordsHidden Markov model relational learning recursive networks
- 1.Bengio, Y.: Neural Networks for Speech and Sequence Recognition. International Thomson Computer Press, London (1996)Google Scholar
- 3.Di Massa, V., Monfardini, G., Sarti, L., Scarselli, F., Maggini, M., Gori, M.: A comparison between recursive neural networks and graph neural networks. In: World Congress on Computational Intelligence, July 2006, pp. 778–785 (2006)Google Scholar
- 4.Hagenbuchner, M., Gori, M., Bunke, H., Tsoi, A.C., Irniger, C.: Using attributed plex grammars for the generation of image and graph databases. Pattern Recognition Letters (Special issue on Graph-based Representations) 24(8), 1081–1087 (2002)Google Scholar