Structure learning in action

By Daniel A. Braun, Carsten Mehring, D. M. Wolpert. 2010

220 citations recorded by the source corpus.

‘Learning to learn’ phenomena have been widely investigated in cognition, perception and more recently also in action. During concept learning tasks, for example, it has been suggested that characteristic features are abstracted from a set of examples with the consequence that learning of similar tasks is facilitated—a process termed ‘learning to learn’. From a computational point of view such an extraction of invariants can be regarded as learning of an underlying structure. Here we review the evidence for structure learning as a ‘learning to learn’ mechanism, especially in sensorimotor control where the motor system has to adapt to variable environments. We review studies demonstrating that common features of variable environments are extracted during sensorimotor learning and exploited for efficient adaptation in novel tasks. We conclude that structure learning plays a fundamental role in skill learning and may underlie the unsurpassed flexibility and adaptability of the motor system.

Subfields: Cognitive Neuroscience, Control and Systems Engineering, Social Psychology

How researchers see this paper

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

In Cognitive Neuroscience

In Control and Systems Engineering

In Social Psychology

Citations in the corpus

Probabilistic Model-Agnostic Meta-Learning (2018, background): “Structure is useful insofar as it yields efficient learning of new tasks – a mechanism known as learning-to-learn, or meta-learning [3].”
Human-level concept learning through probabilistic program induction (2015, background): “6B; ID level not significantly different from chance t(24) = 0.”
Hierarchically Structured Meta-learning (2019, background): “Learning to learn (a.k.a., meta-learning) (Braun et al., 2010), as a common practice to address this challenge, leverages the transferable knowledge learned from previous tasks to improve the learning effectiveness in a new task.”
Intentions and Motor Representations: the Interface Challenge (2017, background): “In particular, there is evidence that parameter learning and structural learning inmotor tasks can be best described as forms of Bayesian inference and modelling (Braun et al. 2009; Braun et al. 2010).”
Attention, learning and the value of information (2012, background): “Neuron 76 , October 18, 2012 ª 2012 Elsevier Inc. 287 Neuron Perspective animals may also possess this capacity (Balan and Gottlieb, 2006; Braun et al., 2010; Johnson et al., 2012).”
Discovering latent causes in reinforcement learning (2015, background): “Recent work has begun to unravel the cognitive and neural mechanisms supporting structure learning (see [2,3] for reviews).”
Dopamine in motivational control: rewarding, aversive, and alerting (2010, background): “All of these phenomena form a remarkable parallel to similar effects seen in sensory and motor adaptation (Braun et al., 2010; Fairhall et al., 2001; Shadmehr et al., 2010), suggesting that they may reflect a general neural mechanism for predictive learning.”
Perception, Action, and Utility: The Tangled Skein (2012, background): “Indeed, numerous authors (Daw et al., 2006; Dayan and Daw, 2008; Braun et al., 2010; Gershman and Niv, 2010; Rao, 2010) have argued that the full problem of decision making under perceptual uncertainty—when both the perceptual state and the utilities are unknown and non-trivial—can essentially be tr”
Probabilistic brains: knowns and unknowns (2013, background): “Structural learning—learning the structure of a task given data 73,74 — is a difficult problem: it is based on an impoverished feedback signal (typically only a positive reward for correct answers) and the reward does not explicitly specify which sensory variables or which motor actions matter.”
Structure Learning in a Sensorimotor Association Task (2010, background): “Rather, structure learning can be regarded as a process of abstraction that extracts general invariants [18].”
Learning latent structure: Carving nature at its joints (2010, background): “The curse of dimensionality can be alleviated if one is willing to make certain assumptions about the structure of the environment or the structure of correct motor strategies [48 ,49 ].”