Recent workhasindicated that,unlikehumans, ImageNet-trained CNNs tendto classify images by texture rather than by shape. How pervasiveis this bias, and wheredoesitcomefrom? Wefindthat,whentrainedondatasets ofimageswith conflicting shape and texture, CNNs learn to classify by shape at least as easily as by texture. What factors, then, produce the texture bias in CNNs trained on ImageNet?

However, the inferred reward function often fails to capture the underlying task objective.

Moreover, they have also been the most quantitatively accurate predictive models of neuronal responses indifferentsensory areasintheprimate brain[57,31,5].