Indiana University, Department of Informatics, 700 N Woodlawn Ave., Bloomington, IN 47408, United States of America.
Cognition. 2020 Jun;199:104192. doi: 10.1016/j.cognition.2020.104192. Epub 2020 Mar 19.
Can newborn brains perform one-shot learning? To address this question, we reared newborn chicks in strictly controlled environments containing a single view of a single object, then tested their object recognition performance across 24 uniformly-spaced viewpoints. We found that chicks can build view-invariant object representations from a single view of an object: a case of one-shot learning in newborn brains. Chicks can also build the same view-invariant object representation from different views of an object, showing that newborn brains converge on common object representations from different sets of sensory inputs. Finally, by rearing chicks with larger numbers of object views, we found that chicks develop enhanced recognition for familiar views. These results illuminate the earliest stages of object recognition, revealing (1) powerful one-shot learning that builds invariant object representations from the first views of an object and (2) view-based learning that enriches object representations, producing enhanced recognition for familiar views.
新生儿的大脑能进行单次学习吗？为了回答这个问题，我们在严格控制的环境中饲养新生小鸡，环境中只包含单一视角的单一物体，然后在 24 个均匀间隔的视角下测试它们的物体识别性能。我们发现，小鸡可以从物体的单一视角建立不变的物体表示：这是新生儿大脑中单次学习的一个例子。小鸡还可以从物体的不同视角建立相同的不变物体表示，这表明新生儿大脑会从不同的感觉输入集合中收敛到共同的物体表示。最后，通过用更多视角的物体来饲养小鸡，我们发现小鸡对熟悉的视角的识别能力增强。这些结果阐明了物体识别的最早阶段，揭示了（1）强大的单次学习，它可以从物体的第一视角建立不变的物体表示，以及（2）基于视图的学习，它丰富了物体表示，从而增强了对熟悉视图的识别。
