Neither hype nor gloom do DNNs justice
arXiv:2312.05355
Abstract
Neither the hype exemplified in some exaggerated claims about deep neural networks (DNNs), nor the gloom expressed by Bowers et al. do DNNs as models in vision science justice: DNNs rapidly evolve, and today's limitations are often tomorrow's successes. In addition, providing explanations as well as prediction and image-computability are model desiderata; one should not be favoured at the expense of the other.
Preprint version of a commentary published by Behavioral and Brain Sciences (https://www.cambridge.org/core/journals/behavioral-and-brain-sciences/article/abs/neither-hype-nor-gloom-do-dnns-justice/639AA5BC7F6E3B91E9B9EC8463D39F77)