The intricate spiraling problems in areas such as aeronautics, bioinformatics, and meteorology require innovative algorithms for intellectual discovery from unique data types and sources. How should “Space Age” intelligent-based systems be capitalizing on the reputable learning classifier systems (LCS)? To make the LCS suitable for resolving knotty real-life problems, Urbanowicz presents the interacting procedures, distinct qualities, and capabilities of ExSTraCS, an “extended supervised tracking and classifying system.”

The tenet of ExSTraCS is predicated on Michigan-style LCS--the rule-based machine learning algorithms for propagating learned patterns over a cooperative population of independently comprehensible classifiers. Like the Michigan-style LCS, ExSTraCS applies reiterative discovery and associates the inclusive search of genetic techniques with inward-looking optimization to corroborate or harmonize learning.

ExSTraCS is designed to lessen the imperatives about data and analytical models, reinforce regulated learning, provide adaptable algorithms for the analysis of diverse data types, and enhance robustness and ease of use. ExSTraCS is implemented in Python to (a) predictably recognize and learn from a mixture of discrete and continuous variables; (b) apply expert knowledge and rules to preprocess data; (c) retain enduring memory of attributes for algorithmic training and feedback; and (d) support rule shrinkage to expedite the detection of information.

The author visibly explains the “data pre-processing, algorithm learning/training, rule population post-processing” phases of ExSTraCS. He provides the details for installing ExSTraCS and performing a six-bit multiplexer analysis. The experimental results with the multiplexer show the easy interpretations of the solutions spread over populations.

The author persuasively presents the resources for providing clear-cut interpretations from rule-population metrics, significance testing, and the visualization of results in ExStraCS. Consequently, I strongly recommend the use of LCS and ExSTraCS for solving difficult problems.