Grammatical Inference Algorithms in MATLAB

Although MATLAB1 has become one of the mainstream languages for the machine learning community, there is still skepticism among the Grammatical Inference (GI) community regarding the suitability of MATLAB for implementing and running GI algorithms. In this paper we will present implementation results of several GI algorithms, e.g., RPNI (Regular Positive and Negative Inference), EDSM (Evidence Driven State Merging), and k-testable machine. We show experimentally based on our MATLAB implementation that state merging algorithms can successfully be implemented and manipulated using MATLAB in the similar fashion as other machine learning tools. Moreover, we also show that MATLAB provides a range of toolboxes that can be leveraged to gain parallelism, speedup etc.

• Type: Conference
• Year: 2010
• Where: ICGI
• Authors: Hasan Ibne Akram, Colin de la Higuera, Huang Xiao, Claudia Eckert
• Keywords: GI Algorithms, ICGI 2010, Machine Learning, MATLAB, Natural Language Processing