Image - Gilboa Iris (Iris haynei) passed through several deep dream generators.
I recently completed a course given by Prof. Yair Weiss ("Lab in computational neuroscience and learning") . In this course, I developed several implementations for classification algorithms of flower images using deep neural networks (DNNs). In the first phase of the project, I present an implementation that successfully classifies a novel dataset with 90% accuracy. In the second phase, I note that both humans and DNNs are excellent classifiers. Then, I use the trained classification networks of the first phase to ask whether the success humans and machines share in terms of function (both are great classifiers) also implies that the two also rely on similar mechanisms for such classification. The short answer - using the limited dataset and methods I checked - is no.
Read the full report here.