Please respond to the “Instructor Question” only. Answer must be in APA format and have at least 250 words. At least 1 reference must be used. The original question and my initial response is also posted below as a reference…but you only need to respond to the instructor question.

Original Question:

Locate research in which mainstream intelligence tests (Stanford-Binet or Wechsler) have been used to assess machine intelligence of systems like Watson (general knowledge) or expert systems (specialized knowledge). Are the results of these assessments valid?

My Response:

The task of trying to enable a humanoid robot to solve simple tasks through the use of the Stanford-Binet test is seen in the thesis (Schenk, 2013). The research uses an upper torso humanoid robot to perform a set of three reasoning tasks. The aim of the test was to show the abilities of the robot in the intelligence aspect and improve its abilities through the performance of real-world tasks. The task of the robot was to select the correct solution from a set of choices. The results were that the robot selected less than half the correct solutions. The validity of these results cannot be ascertained since there were no subtests. The lack of subtests could not verify the validity of the results in the study.

The other case showed the use of a Wechsler test using a simple humanoid. As shown in the research by Legg and Hutter (2007), the test administered in a similar fashion as the Stanford-Binet shows a definition of intelligence. The test involved several re-tests in the machine. The four main categories targeted were reasoning, retention of information, the organization of information and the processing input. The results from the test showed a complete failure by the machine to comprehend, organize, and retain the information. The results were not valid since the test is essential for human intelligence testing rather than artificial testing. The two tests, therefore, are suitable for human intelligence testing and are not applicable for machine intelligence testing.

References:

Legg, S. & Hutter, M. (2007). Universal Intelligence: A Definition of Machine Intelligence. Minds and Machines, 17(4), 391–444. New York: Springer.

Schenk, C. (2013). Intelligence tests for robots: Solving perceptual reasoning tasks with a humanoid robot. Ames, IA: Iowa State University.

Instructor Question:

Do you think the tests are fair for a machine that has unlimited memory and/or recall ability from previously acquired information?

Do you need a similar assignment done for you from scratch? We have qualified writers to help you. We assure you an A+ quality paper that is free from plagiarism. Order now for an Amazing Discount!
Use Discount Code "Newclient" for a 15% Discount!

NB: We do not resell papers. Upon ordering, we do an original paper exclusively for you.