.png){kind=icon}
.png){kind=icon}
Return
Human-level concept learning through probabilistic program induction
.png){kind=icon}
OA
AI
DOI：10.1126/science.aab3050.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
People learning new concepts can often generalize successfully from just a single example, yet machine learning algorithms typically require tens or hundreds of examples to perform with similar accuracy. People can also use learned concepts in richer ways than conventional algorithms-for action, imagination, and explanation. We present a computational model that captures these human learning abilities for a large class of simple visual concepts: handwritten characters from the world's alphabets. The model represents concepts as simple programs that best explain observed examples under a Bayesian criterion. On a challenging one-shot classification task, the model achieves human-level performance while outperforming recent deep learning approaches. We also present several visual Turing tests probing the model's creative generalization abilities, which in many cases are indistinguishable from human behavior.
Keywords:
NEURAL-NETWORKS
MODEL
EXEMPLAR
LANGUAGE
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
45.8
Papers:
1.4W
Citations:
78.6W