Measuring the accuracy of computer models
It really impresses me as we continue to make advances in the reproduction of human senses or capabilities in silicon and software. What really caught my eye about this article was thinking about the fact that the accuracy of the model can be measured not only by it's success at mirroring human-like abilities ... but that it also makes errors in a way that is similar to humans.
Once the models are solid enough, then they will be able to learn from the errors in humans ... and potentially due to shear quantity, scale, or speed exceed our human abilities. Closer and closer to the Singularity we move each day ...
Computer Model Behaves Like Humans On Visual Categorization Task. In a new MIT study, a computer model designed to mimic the way the brain itself processes visual information performs as well as humans do on rapid categorization tasks.
The model even tends to make similar errors as humans, possibly because it s... [KurzweilAI.net Accelerating Intelligence News]