Human-level concept learning through probabilistic program induction
Science, 2015. [All Versions]. [Preprint]. [Supplementary Material]. 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…
- from
- AGI & CoCoSci
- added
- 2026-10-10
- likes
- 0
similar
-
Bayesian modeling of human concept learning proceedings.neurips.cc
NeurIPS'98, 1998. [All Versions]. [Preprint]. This work considers the problem of learning concepts from small numbers of positive examples, a feat which humans perform routinely but which computers are rarely capable of. Bridging machine learning and cognitive science…
-
Human-level few-shot concept induction through minimax entropy learning science.org
Science Advances, 2024. [All Versions]. This paper introduces a computational model designed to emulate human inductive reasoning on abstract reasoning tasks, such as those in IQ tests, using a minimax entropy approach. This method combines identifying the most effective…
-
Human-like property induction is a challenge for large language models charleskemp.com
CogSci'22, 2022.
-
Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs science.org
Science Robotics, 2019. [All Versions]. Humans can infer concepts from image pairs and apply those in the physical world in a completely different setting, enabling tasks like IKEA assembly from diagrams. If robots could represent and infer high-level concepts, then it would…
-
Probabilistic machine learning and artificial intelligence nature.com
Nature, 2015. [All Versions]. Probabilistic modelling provides a framework for understanding what learning is, and has therefore emerged as one of the principal theoretical and practical approaches for designing machines that learn from data acquired through experience. The…
-
Theory-based Bayesian models of inductive learning and reasoning cell.com
Trends in Cognitive Sciences, 2006. [All Versions]. [Preprint]. Inductive inference allows humans to make powerful generalizations from sparse data when learning about word meanings, unobserved properties, causal relationships, and many other aspects of the world. Traditional…
AGI & CoCoSci › Papers > Bayesian Modeling > Bayesian Induction: “Science, 2015. [All Versions]. [Preprint]. [Supplementary Material]. 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…”