期刊
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
卷 14, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fncom.2020.586671
关键词
transfer learning; few-shot learning; semantic cognition; artificial neural networks; object recognition
资金
- Lawrence Livermore National Laboratory of the U.S. Department of Energy [DE-AC52-07NA27344]
- LLNL-LDRD Program [COMP-19-ERD-007]
- National Science Foundation [1026934, 1232530, 1122374, 1745302]
- Division Of Behavioral and Cognitive Sci
- Direct For Social, Behav & Economic Scie [1026934] Funding Source: National Science Foundation
- Division Of Behavioral and Cognitive Sci
- Direct For Social, Behav & Economic Scie [1232530] Funding Source: National Science Foundation
Humans can quickly and accurately learn new visual concepts from sparse data, sometimes just a single example. The hierarchical organization of artificial neural networks plays a critical role in improving learning speed and accuracy.
Humans quickly and accurately learn new visual concepts from sparse data, sometimes just a single example. The impressive performance of artificial neural networks which hierarchically pool afferents across scales and positions suggests that the hierarchical organization of the human visual system is critical to its accuracy. These approaches, however, require magnitudes of order more examples than human learners. We used a benchmark deep learning model to show that the hierarchy can also be leveraged to vastly improve the speed of learning. We specifically show how previously learned but broadly tuned conceptual representations can be used to learn visual concepts from as few as two positive examples; reusing visual representations from earlier in the visual hierarchy, as in prior approaches, requires significantly more examples to perform comparably. These results suggest techniques for learning even more efficiently and provide a biologically plausible way to learn new visual concepts from few examples.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据