2000 character limit reached
Neither hype nor gloom do DNNs justice
Published 8 Dec 2023 in cs.LG, cs.CV, and q-bio.NC | (2312.05355v1)
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.
- Deep convolutional networks do not classify based on global object shape. PLOS Computational Biology, 14(12):e1006613.
- Mixed Evidence for Gestalt Grouping in Deep Neural Networks. arXiv:2203.07302 [cs].
- Deep problems with neural network models of human vision. Behavioral and Brain Sciences, pages 1–74.
- Scaling vision transformers to 22 billion parameters. arXiv preprint arXiv:2302.05442.
- How does the brain solve visual object recognition? Neuron, 73(3):415–434.
- Crowding reveals fundamental differences in local vs. global processing in humans and machines. Vision Research, 167:39–45.
- Partial success in closing the gap between human and machine vision. In Advances in Neural Information Processing Systems 34.
- Can machine learning account for human visual object shape similarity judgments? Vision Research, 167:87–99.
- Intemann, K. (2020). Understanding the problem of “hype”: Exaggeration, values, and trust in science. Canadian Journal of Philosophy, pages 1–16.
- Building machines that learn and think like people. Behavioral and Brain Sciences, 40:e253.
- The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision. In International Conference on Learning Representations.
- Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation. arXiv:2204.02283 [cs].
- Pearl, J. (2009). Causality. Cambridge University Press, Cambridge, 2nd edition.
- Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nature Neuroscience, 2(1):79–87. tex.date-modified: 2020-05-03 20:14:10 +0200.
- Are deep neural networks adequate behavioural models of human visual perception? Annual Review of Vision Science, 9:(in press).
- Neither hype nor gloom do DNNs justice. Behavioral and Brain Sciences, 46:e412.
Paper Prompts
Sign up for free to create and run prompts on this paper.
