Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency
A central problem in cognitive science and behavioural neuroscience as well as in machine
learning and artificial intelligence research is to ascertain whether two or more decision …
learning and artificial intelligence research is to ascertain whether two or more decision …
Trivial or impossible--dichotomous data difficulty masks model differences (on ImageNet and beyond)
" The power of a generalization system follows directly from its biases"(Mitchell 1980).
Today, CNNs are incredibly powerful generalisation systems--but to what degree have we …
Today, CNNs are incredibly powerful generalisation systems--but to what degree have we …
[HTML][HTML] Deciphering image contrast in object classification deep networks
A Akbarinia, R Gil-Rodriguez - Vision Research, 2020 - Elsevier
The ultimate goal of neuroscience is to explain how complex behaviour arises from neuronal
activity. A comparable level of complexity also emerges in deep neural networks (DNNs) …
activity. A comparable level of complexity also emerges in deep neural networks (DNNs) …
Imagenet suffers from dichotomous data difficulty
" The power of a generalization system follows directly from its biases"(Mitchell 1980).
Today, CNNs are incredibly powerful generalisation systems---but to what degree have we …
Today, CNNs are incredibly powerful generalisation systems---but to what degree have we …