Rational Use of Cognitive Resources: Levels of Analysis Between the Computational and the Algorithmic

By T. Griffiths, Falk Lieder, Noah D. Goodman. 2015

406 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning from Physical Human Corrections, One Feature at a Time (2018, background): “Ideally, the human’s correction will only affect the cup’s distance from the table; in practice, however, human actions are noisy and imperfect [7, 19, 20, 24], especially when kinesthetically maneuvering robotic manipulators while trying to carefully orchestrate their multiple degrees of freedom [1”
Automatically Composing Representation Transformations as a Means for Generalization (2018, background): “Instead of learning an algorithm to learn, the learner can learn an algorithm to reason: casting the generalization problem as an algorithm design problem is a growing hypothesis for the mechanism with which humans can generalize to new scenarios [15, 36, 54].”
Occam's razor is insufficient to infer the preferences of irrational agents (2017, background): “The related ideas of meta-reasoning [Russell, 2016], computational rationality [Lewis et al., 2014] and resource rationality [Grifﬁths et al., 2015] may create the possibility to redeﬁne irrational behavior as rational in an ‘ancestral’ distribution of environments where the agent optimises its…”
Doing more with less: meta-reasoning and meta-learning in humans and machines (2019, background): “These two components of human intelligence — efficient use of computational resources [3,4] and efficient use of data — relate to two problems that have been studied in the AI literature: meta-reasoning and meta-learning.”