A Developmental Approach to Machine Learning?
By Linda B. Smith, Lauren K Slone. 2017
101 citations recorded by the source corpus.
Visual learning depends on both the algorithms and the training material. This essay considers the natural statistics of infant- and toddler-egocentric vision. These natural training sets for human visual object recognition are very different from the training data fed into machine vision systems. Rather than equal experiences with all kinds of things, toddlers experience extremely skewed distributions with many repeated occurrences of a very few things. And though highly variable when considered as a whole, individual views of things are experienced in a specific order – with slow, smooth visual changes moment-to-moment, and developmentally ordered transitions in scene content. We propose that the skewed, ordered, biased visual experiences of infants and toddlers are the training data that allow human learners to develop a way to recognize everything, both the pervasively present entities and the rarely encountered ones. The joint consideration of real-world statistics for learning by researchers of human and machine learning seems likely to bring advances in both disciplines.
Subfields: Artificial Intelligence, Cognitive Neuroscience, Developmental and Educational Psychology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Cognitive Neuroscience
In Developmental and Educational Psychology
Citations in the corpus
- Continual egocentric object recognition (2019, background): “• Progressively introduce novel objects in a developmental fashion [3, 31], and provide supervision on-demand in an online active learning fashion.”
- Reward Shaping via Meta-Learning (2019, background): “The ability to quickly solve new similar tasks drawn from such distributions is much expected for general intelligence, since it is mastered by human infants quite young (Smith & Slone, 2017).”
- Adaptive Cross-Modal Few-Shot Learning (2019, background): “On the other hand, existing evidence suggests that human visual system is capable of effectively operating in small data regime: humans can learn new concepts from a very few samples, by leveraging prior knowledge and context [23, 30, 46].”
- Probing Physics Knowledge Using Tools from Developmental Psychology (2018, background): “Second, it will be of interest to further separate our train and test sets, ideally moving to training with more free-form, naturalistic data (Kay et al., 2017), or even video data from infant studies (Clerkin et al., 2017; Smith & Slone, 2017).”