How do machines learn? Evaluating the AIcon2abs method

This paper evaluates AIcon2abs (Queiroz et al., 2021), a recently proposed method that enables awareness among the general public on machine learning. Such is possible due to the use of WiSARD, an easily understandable machine learning mechanism, thus requiring little effort and no technical background from the target users. WiSARD is adherent to digital computing; training consists of writing to RAM-type memories, and classification consists of reading from these memories. The model enables easy visualization and understanding of training and classification tasks' internal realization through ludic activities. Furthermore, the WiSARD model does not require an Internet connection for training and classification, and it can learn from a few or one example. This feature makes it easier to observe the machine, increasing its accuracy on a particular task with each new example used. WiSARD can also create "mental images" of what it has learned so far, evidencing key features pertaining to a given class. The assessment of the AIcon2abs method's effectiveness was conducted through the evaluation of a remote course with a workload of approximately 6 hours. It was completed by thirty-four Brazilian subjects: 5 children between 8 and 11 years old; 5 adolescents between 12 and 17 years old; and 24 adults between 21 and 72 years old. Data analysis adopted a hybrid approach. AIcon2abs was well-rated by almost 100% of the research subjects, and the data collected revealed quite satisfactory results concerning the intended outcomes. This research has been approved by the CEP/HUCFF/FM/UFRJ Human Research Ethics Committee.