Fixing the problems of deep neural networks will require better training data and learning algorithms

Over the past decade, vision scientists have turned to deep neural networks (DNNs) to model biological vision. The popularity of DNNs comes from their ability to rival human performance on visual tasks [1] and the seemingly concomitant correspondence of their hidden units with biological vision [2]. Bowers and colleagues [3] marshal evidence from psychology and neuroscience to argue that while DNNs and biological systems may achieve similar accuracy on visual benchmarks, they often do so by relying on qualitatively different visual features and strategies [4-6]. Based on these findings, Bowers and colleagues call for a re-evaluation of what DNNs can tell us about biological vision and suggest dramatic adjustments going forward, potentially even moving on from DNNs altogether. Are DNNs poorly suited to model biological vision?