| Comparison between Standard and Simplified Rating Methods |
| Standard Rating | Simplified Rating | |
| Applicability | Only existing implementations | Models, architectures, designs, implementations |
| Accuracy | High (realistic metric) | Low (potential, optimistic metric) |
| Cost | High (internal inspection of the implementation, cognitive tests design and execution) | Low (architectural components and cognitive skills are inferred directly) |
| CQS Computation Time | Within milliseconds | Within milliseconds |
| Problem Domain | Domain-dependent* | Domain-independent |
| Required Resources | Suitable testing environment, test procedures and associated tools, data collection / inspection / observation tools | Detailed description of the system |
| Output | ConsScale Level, Cognitive Profile, Quantitative Score | ConsScale Level, Cognitive Profile, Quantitative Score |
| Online Resources | ConsScale Calculator | ConsScale Calculator |
| * Actual cognitive tests are of necessity domain-dependent. They have to be performed in particular frameworks and real settings. Even the Turing test (level 10), is domain-dependent. Some authors have argued that Turing test is general-purpose, but is indeed specific to the domain of human accurate verbal interaction. |
| < Prev | Next > |
|---|
ConsScale - ConsScale Rating
New Scientist. 05 June 2010. Cover Story. pp. 28-31. The topic of mind uploading is addressed in the cover story of this New Scientist issue. ConsScale is quoted as an practical tool to really assess to what extent artificial avatars can be considered as conscious as ourselves. |
www.Conscious-Robots.com is a website about Machine Consciousness and Cognitive Robotics. The Test for Consciousness forum is the place for open discussion about ConsScale and other metrics for consciousness.