Name
Abstract | ||
|---|---|---|
Real-world learning systems have practical limitations on the quality and quantity of the training datasets that they can collect and consider. How should a system go about choosing a subset of the possible training examples that still allows for learning accurate, generalizable models? To help address this question, we draw inspiration from a highly efficient practical learning system: the human child. Using head-mounted cameras, eye gaze trackers, and a model of foveated vision, we collected first-person (egocentric) images that represent a highly accurate approximation of the "training data" that toddler's visual systems collect in everyday, naturalistic learning contexts. We used state-of-the-art computer vision learning models (convolutional neural networks) to help characterize the structure of these data, and found that child data produce significantly better object models than egocentric data experienced by adults in exactly the same environment. By using the CNNs as a modeling tool to investigate the properties of the child data that may enable this rapid learning, we found that child data exhibit a unique combination of quality and diversity, with not only many similar large, high-quality object views but also a greater number and diversity of rare views. This novel methodology of analyzing the visual "training data" used by children may not only reveal insights to improve machine learning, but also may suggest new experimental tools to better understand infant learning in developmental psychology. |
Year | Venue | Keywords |
|---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | machine learning,convolutional neural networks,a system,computer vision,visual system,principal component analysis,learning systems,toddler-inspired visual object learning,object learning,developmental psychology,visual training,rapid learning,eye gaze |
Field | DocType | Volume |
Training set,BitTorrent tracker,Convolutional neural network,Toddler,Computer science,Eye tracking,Learning models,Artificial intelligence,Machine learning | Conference | 31 |
ISSN | Citations | PageRank |
1049-5258 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Sven Bambach | 1 | 64 | 5.77 |
| D. Crandall | 2 | 2111 | 168.58 |
| Linda B. Smith | 3 | 83 | 12.05 |
| Chen Yu | 4 | 185 | 22.81 |