The ubiquitous and demonstrably suboptimal choice of resizing images to ...
How do neural networks extract patterns from pixels? Feature visualizati...
Deep neural networks (DNNs) are machine learning algorithms that have
re...
Widely observed neural scaling laws, in which error falls off as a power...
In laboratory object recognition tasks based on undistorted photographs,...
"The power of a generalization system follows directly from its biases"
...
One widely used approach towards understanding the inner workings of dee...
A few years ago, the first CNN surpassed human performance on ImageNet.
...
Feature visualizations such as synthetic maximally activating images are...
How do humans learn to acquire a powerful, flexible and robust represent...
A central problem in cognitive science and behavioural neuroscience as w...
Deep learning has triggered the current rise of artificial intelligence ...
The ability to detect objects regardless of image distortions or weather...
Convolutional Neural Networks (CNNs) are commonly thought to recognise
o...
We compare the robustness of humans and current convolutional deep neura...
Human visual object recognition is typically rapid and seemingly effortl...