APPLYING METRICS TO MACHINE-LEARNING TOOLS - A KNOWLEDGE ENGINEERING APPROACH

The field of knowledge engineering has been one of the most visible su ccesses of AI to date. Knowledge acquisition is the main bottleneck in the knowledge engineer's work. Machine-learning tools have contribute d positively to the process of trying to eliminate or open up this bot tleneck, but how do we know whether the field is progressing? How can we determine the progress made in any of its branches? How can we be s ure of an advance and take advantage of it? This article proposes a be nchmark as a classificatory, comparative, and metric criterion for mac hine-learning tools. The benchmark centers on the knowledge engineerin g viewpoint, covering some of the characteristics the knowledge engine er wants to find in a machine-learning tool. The proposed model has be en applied to a set of machine-learning tools, comparing expected and obtained results. Experimentation validated the model and led to inter esting results.