TY - GEN
T1 - One shot learning of simple visual concepts
AU - Lake, Brenden M.
AU - Salakhutdinov, Ruslan
AU - Gross, Jason
AU - Tenenbaum, Joshua B.
N1 - Publisher Copyright:
© CogSci 2011.
PY - 2011
Y1 - 2011
N2 - People can learn visual concepts from just one example, but it remains a mystery how this is accomplished. Many authors have proposed that transferred knowledge from more familiar concepts is a route to one shot learning, but what is the form of this abstract knowledge? One hypothesis is that the sharing of parts is core to one shot learning, and we evaluate this idea in the domain of handwritten characters, using a massive new dataset. These simple visual concepts have a rich internal part structure, yet they are particularly tractable for computational models. We introduce a generative model of how characters are composed from strokes, where knowledge from previous characters helps to infer the latent strokes in novel characters. The stroke model outperforms a competing state-of-the-art character model on a challenging one shot learning task, and it provides a good fit to human perceptual data.
AB - People can learn visual concepts from just one example, but it remains a mystery how this is accomplished. Many authors have proposed that transferred knowledge from more familiar concepts is a route to one shot learning, but what is the form of this abstract knowledge? One hypothesis is that the sharing of parts is core to one shot learning, and we evaluate this idea in the domain of handwritten characters, using a massive new dataset. These simple visual concepts have a rich internal part structure, yet they are particularly tractable for computational models. We introduce a generative model of how characters are composed from strokes, where knowledge from previous characters helps to infer the latent strokes in novel characters. The stroke model outperforms a competing state-of-the-art character model on a challenging one shot learning task, and it provides a good fit to human perceptual data.
KW - Bayesian modeling
KW - category learning
KW - neural networks
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85135606166&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135606166&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85135606166
T3 - Expanding the Space of Cognitive Science - Proceedings of the 33rd Annual Meeting of the Cognitive Science Society, CogSci 2011
SP - 2568
EP - 2573
BT - Expanding the Space of Cognitive Science - Proceedings of the 33rd Annual Meeting of the Cognitive Science Society, CogSci 2011
A2 - Carlson, Laura
A2 - Hoelscher, Christoph
A2 - Shipley, Thomas F.
PB - The Cognitive Science Society
T2 - 33rd Annual Meeting of the Cognitive Science Society: Expanding the Space of Cognitive Science, CogSci 2011
Y2 - 20 July 2011 through 23 July 2011
ER -