Autor:	Dulberg, Zachary, Cohen, Jonathan
Rok vydání:	2020
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Humans understand a set of canonical geometric transformations (such as translation and rotation) that support generalization by being untethered to any specific object. We explore inductive biases that help a neural network model learn these transformations in pixel space in a way that can generalize out-of-domain. Specifically, we find that high training set diversity is sufficient for the extrapolation of translation to unseen shapes and scales, and that an iterative training scheme achieves significant extrapolation of rotation in time. Comment: NeurIPS 2020 Workshop on BabyMind
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2011.08822 Zobrazit plný text záznamu View this record from Arxiv