Shortcut Learning in Deep Neural Networks · HackerPapers discussions

Shortcut Learning in Deep Neural Networks — mentioned by MindGods

Sat, 25 Jul 2020 20:21:04 GMT

Link to paper: https://arxiv.org/abs/2004.07780

Paper and discussion history. A mention is not an endorsement.

Shortcut Learning in Deep Neural Networks — mentioned by ArtWomb

Wed, 10 Jun 2020 12:02:34 GMT

Humans observe an object once, such as a cup for drinking water, and we immediately grasp its "cupness". We can identify infinite varieties of cups despite variations in morphology, design, utility and context. Simply based on a single learning instance. This absence of any neural theory of inference is at the crux of the problem ;) Shortcut Learning in Deep Neural Networks https://arxiv.org/abs/2004.07780

Paper and discussion history. A mention is not an endorsement.

Shortcut Learning in Deep Neural Networks — HN submission

Sat, 18 Apr 2020 01:28:33 GMT

Shortcut Learning in Deep Neural Networks

3 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.