![]() A person and a computer, being separated in two rooms, answer the tester’s questions on-line. ![]() We show how some disciplines and places have affinities towards certain type of tests, and which tests are more influential according to scientometric indicators. ![]() Behavior tests are more synthetic and more practicable, but give a stronger role to ex post human interpretation of behavior. Architecture tests main advantage is that they could apparently test for qualia, a feature that is getting an increasing attention in recent years. Each category has its strengths and weaknesses. The tests put forward in their work typically fall under one of two grand categories: architecture (the presence of consciousness is inferred from the correct implementation of a relevant architecture) and behavior (the presence of consciousness is deduced by observing a specific behavior). This paper provides an analytic review of the existing tests for machine consciousness proposed in the academic literature over the past decade and an overview of the diverse scientific communities involved in this enterprise. The accelerating advances in the fields of neuroscience, artificial intelligence, and robotics have been reviving interest and raising new philosophical, ethical or practical questions that depend on whether or not there may exist a scientific method of probing consciousness in machines.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |