AUTHOR=Rule Joshua S. , Riesenhuber Maximilian TITLE=Leveraging Prior Concept Learning Improves Generalization From Few Examples in Computational Models of Human Object Recognition JOURNAL=Frontiers in Computational Neuroscience VOLUME=14 YEAR=2021 URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2020.586671 DOI=10.3389/fncom.2020.586671 ISSN=1662-5188 ABSTRACT=

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.