Generative adversarial networks (GANs) have recently become a hot research topic; however, they have been studied since 2014, and a large number of algorithms have been …
Artificial neural networks (ANNs) inspired by biology are beginning to be widely used to model behavioural and neural data, an approach we call 'neuroconnectionism'. ANNs have …
Deep learning models are vulnerable to adversarial examples. As a more threatening type for practical deep learning systems, physical adversarial examples have received extensive …
Neuroscience research is undergoing a minor revolution. Recent advances in machine learning and artificial intelligence research have opened up new ways of thinking about …
Recent work has indicated that, unlike humans, ImageNet-trained CNNs tend to classify images by texture rather than by shape. How pervasive is this bias, and where does it come …
Non-recurrent deep convolutional neural networks (CNNs) are currently the best at modeling core object recognition, a behavior that is supported by the densely recurrent …
While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this …
We evaluate a wide range of ImageNet models with five trained human labelers. In our year- long experiment, trained humans first annotated 40,000 images from the ImageNet and …
FA Wichmann, R Geirhos - Annual Review of Vision Science, 2023 - annualreviews.org
Deep neural networks (DNNs) are machine learning algorithms that have revolutionized computer vision due to their remarkable successes in tasks like object classification and …