framework
active
framework:contrastive-learning

Contrastive learning

Supervised learning framework where system learns by observing contrast between current response and nudged improved response; requires weak additional forces from supervisor

Neighborhood — ranked by edge-count

Papers (2)

paper

Methods (4)

method
  • Binary NCE Loss
    implements
    One of two contrastive objectives analyzed; shown to be minimized by PMI kernel representation
  • InfoNCE Loss
    implements
    One of two contrastive objectives analyzed; shown to be minimized by PMI kernel representation up to scaling
  • SimCSE
    implements
    Contrastive sentence embedding method used in color cooccurrence experiment; represents contrastive language learner
  • SimCLR
    implements
    Self-supervised contrastive learning method cited as instance of NCE-type objectives that converge to PMI kernel

Concepts (1)

concept

Frameworks (2)

framework
  • Physical learning
    associated_with
    Framework for solving inverse problems in which physical systems autonomously adapt their parameters in response to stimuli through local learning rules, without requiring computational design or explicit cost functions
  • Contrastive Sparse AutoEncoder (CV-SAE) Framework
    implements
    The primary novel framework introduced in the paper for learning facet-level personality control vectors

Hypotheses (1)

hypothesis

Conceptual bridges

2-hop · via this framework's ideas

Where ideas in this framework connect to the rest of the corpus — the same concept, an analogy, or a restatement elsewhere.

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.

  • Contrastive analysismethod0.826
    Method comparing brain activity in conscious vs. unconscious conditions.
  • Contrastconcept0.804
    The property that living structures contain intense contrast—far more than one imagines helpful; true opposites which annihilate each other when superimposed, creating differentiation that gives birth to something; contrast unifies rather than separates when used correctly
  • Perceptual Learningconcept0.796
    Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
  • Contrastive Learning Ablation Studymethod0.795
    Three-setting ablation (Before Training, Without CL, With CL) to isolate the contribution of contrastive learning
  • Associative Learningconcept0.792
    Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
  • Contrastive Pairsconcept0.787
    Pairs of prompts at different reflection levels used to compute steering vectors.
  • Learningconcept0.782
    Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
  • Epistemic Learningconcept0.773
    Learning model parameters through curious, uncertainty-reducing behavior; reducing ignorance about contingencies