How saccadic vision might help with theinterpretability of deep networks
arXiv:2105.13264
Abstract
We describe how some problems (interpretability,lack of object-orientedness) of modern deep networks potentiallycould be solved by adapting a biologically plausible saccadicmechanism of perception. A sketch of such a saccadic visionmodel is proposed. Proof of concept experimental results areprovided to support the proposed approach.
References in corpus (5)
- A systematic study of the class imbalance problem in convolutional neural networks
- AutoML: A Survey of the State-of-the-Art
- Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future
- Making Convolutional Networks Shift-Invariant Again
- Measuring Catastrophic Forgetting in Neural Networks