Title |
A Developmental Approach to Machine Learning?
|
---|---|
Published in |
Frontiers in Psychology, December 2017
|
DOI | 10.3389/fpsyg.2017.02124 |
Pubmed ID | |
Authors |
Linda B Smith, Lauren K Slone |
Abstract |
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. |
X Demographics
As of 1 July 2024, you may notice a temporary increase in the numbers of X profiles with Unknown location. Click here to learn more.
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 19 | 14% |
United Kingdom | 8 | 6% |
France | 2 | 1% |
Canada | 2 | 1% |
Australia | 2 | 1% |
Japan | 2 | 1% |
Switzerland | 2 | 1% |
Denmark | 1 | <1% |
Nigeria | 1 | <1% |
Other | 12 | 9% |
Unknown | 87 | 63% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 89 | 64% |
Scientists | 47 | 34% |
Practitioners (doctors, other healthcare professionals) | 2 | 1% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 163 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 30 | 18% |
Student > Master | 21 | 13% |
Researcher | 20 | 12% |
Student > Bachelor | 15 | 9% |
Student > Doctoral Student | 14 | 9% |
Other | 23 | 14% |
Unknown | 40 | 25% |
Readers by discipline | Count | As % |
---|---|---|
Psychology | 31 | 19% |
Computer Science | 29 | 18% |
Neuroscience | 12 | 7% |
Linguistics | 7 | 4% |
Engineering | 7 | 4% |
Other | 24 | 15% |
Unknown | 53 | 33% |