claim

active

claim:perceptual-learning-is-literally-an-integral-part-of-value-learning-necessary-to-integrate-out-dependencies-on-inferred-causes-of-sensory-information

Perceptual learning is literally an integral part of value learning, necessary to integrate out dependencies on inferred causes of sensory information.

Core unifying claim: perception and value-learning are unified through free energy minimization.

Source paper

extracted_from

A Free energy principle for the brain (lecture summary)

(2008) · Karl Friston

Neighborhood — ranked by edge-count

Communities (2)

community

Chain-of-Thought reasoning robustness & safety
members_of
CoT effects on generalization, multimodal QA accuracy, and AI safety alignment training.
Sensory integration in predictive cognition
members_of
Framework viewing perception as active inference mechanism that reduces hallucination through multimodal feature integration and predictive model compression.

Concepts (2)

concept

Perceptual Learning
associated_withsupports
Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
Value Learning
associated_withsupports
Field of research integrating reward learning and optimization; shown to be unified with perceptual learning via free energy principle.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

perceptual learning is, literally, an integral part of value learningquote0.940
Key assertion that perceptual and value learning are inseparable.
acting to optimize value and perception are two aspects of exactly the same principle; namely the minimisation of a quantity [free energy] that bounds the probability of sensory input, given a particular agent or phenotype.quote0.775
Concise statement of the free-energy principle's unification of action and perception.
Reinforcement learning acting on individual characteristics affecting their connections to others can result in dynamics that are equivalent to unsupervised learning at the system scale.claim0.765
Key insight linking individual rewards to system-level learning.
value is simply the probability of sensory input expected by an agent.quote0.759
Redefinition of value in probabilistic terms.
Value is the probability of sensory input expected by an agentclaim0.756
Redefines value in probabilistic terms, linking to surprise minimisation.
A physical learning system thus has the following ingredients: Physical d.o.f s that respond to external stimuli f by adopting a state or dynamic behavior s(f), a subset of which defines the desired behavior (i.e., output); Learning d.o.f wi that can modify how the physical d.o.f s(f; {wi}) respond to external stimuli f; A learning rule, dwi = h(s(f; {wi}))dt, that modifies the learning d.o.f wi based on the response of the physical d.o.f s to the stimuli f.quote0.755
Foundational definition of physical learning system components; load-bearing for understanding the entire framework
"Pain is a core component of adaptive learning...signals that encode internal evaluations that guide the agent through complex environments."quote0.754
Load-bearing motivation for using pain as a learning signal in the computational framework
"[W]e must confess that perception, and what depends upon it, is inexplicable in terms of mechanical reasons... when inspecting its interior, we will find only parts that push one another, and we will never find anything to explain a perception."quote0.752
Canonical illustration of the Hard Problem intuition that any functional/mechanical explanation faces an explanatory gap for perception