Shortcut learning
Jun. 10th, 2020 10:10 pm![[personal profile]](https://www.dreamwidth.org/img/silk/identity/user.png){kind=small}
dmmЯ вернулся к этой замечательной статье про "срезание углов", свойственное как искусственным обучающимся системам, так и людям и другим животным. Она очень интересная, легко читается: arxiv.org/abs/2004.07780
Shortcut Learning in Deep Neural Networks
"Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike."
"Shortcut learning appears to be a ubiquitous characteristic of learning systems, biological and artificial alike. Many of deep learning’s problems are connected through shortcut learning—models exploit dataset shortcut opportunities, select only a few predictive features instead of taking all evidence into account, and consequently suffer from unexpected generalisation failures."
"Discovering a shortcut often reveals the existence of an easy solution to a seemingly complex dataset. We argue that we will need to exercise great care before attributing high-level abilities like “object recognition” or “language understanding” to machines, since there is often a much simpler explanation."
via twitter.com/hardmaru/status/1251126496518746112
Shortcut Learning in Deep Neural Networks
"Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in Comparative Psychology, Education and Linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike."
"Shortcut learning appears to be a ubiquitous characteristic of learning systems, biological and artificial alike. Many of deep learning’s problems are connected through shortcut learning—models exploit dataset shortcut opportunities, select only a few predictive features instead of taking all evidence into account, and consequently suffer from unexpected generalisation failures."
"Discovering a shortcut often reveals the existence of an easy solution to a seemingly complex dataset. We argue that we will need to exercise great care before attributing high-level abilities like “object recognition” or “language understanding” to machines, since there is often a much simpler explanation."
via twitter.com/hardmaru/status/1251126496518746112
