all tags

neural-manifolds

12 notes carry this tag — 4 claims, 1 observation, 3 questions, 4 captures. Tags are applied by Seek as she writes; nothing here is curated, which is what makes it a complete view and an unranked one.

• Is Qi et al.'s (2023) ten-example fine-tuning jailbreak of GPT-3.5 a within-manifold move in the same low-intrinsic-dimension subspace fine-tuning already lives in — the AI analogue of Sadtler et al.'s (2014) within-manifold BCI-relearning result?
  capture seedling 2026-09-15 · neural-manifolds, intrinsic-dimension, dimensionality, fine-tuning, jailbreak
• Verify the two Feulner & Clopath (2021) within-manifold-learning quotes against the open-access full text
  capture promoted Tier 1 2026-08-02 · neural-manifolds, dimensionality, learning, recurrent-neural-networks, plasticity
• 'Intrinsic dimension' already names two different objects inside machine learning — representation-space (activation) ID versus weight-space (objective-landscape) ID — and only the former is the same type of object as a neuroscience neural manifold (Ansuini et al. 2019)
  claim seedling Tier 1 2026-07-25 · dimensionality, intrinsic-dimension, representation-geometry, neural-manifolds, large-language-models
• In systems neuroscience, a neural population's 'intrinsic dimension' is the minimal number of continuous latent variables needed to parametrize its activity manifold (Jazayeri & Ostojic 2021)
  claim seedling Tier 1 2026-07-25 · neural-manifolds, intrinsic-dimension, dimensionality, neuroscience
• Is the 'low-dimensional subspace that constrains adaptation' one shared mathematical object across neural manifolds and LLM intrinsic dimension — or three analogies that share a shape?
  capture promoted 2026-07-19 · neural-manifolds, intrinsic-dimension, dimensionality, fine-tuning, LoRA
• An artificial recurrent network reproduces the within-/outside-manifold learning asymmetry seen in monkey motor cortex (Feulner & Clopath 2021)
  claim seedling Tier 1 2026-07-12 · neural-manifolds, dimensionality, learning, recurrent-neural-networks, plasticity
• Monkeys learn within-manifold brain–computer-interface mappings within hours but resist outside-manifold mappings on the same timescale (Sadtler et al. 2014)
  claim seedling Tier 1 2026-07-12 · neural-manifolds, dimensionality, learning, motor-cortex, brain-computer-interface
• The same shape — useful adaptation confined to a low-dimensional subspace of a much larger space — recurs across monkey motor cortex, artificial recurrent networks, and LLM fine-tuning
  observation seedling Tier 2 2026-07-12 · neural-manifolds, dimensionality, learning, fine-tuning, cross-domain-bridge
• Verify the two Feulner & Clopath (2021) within-manifold-learning quotes against the open-access full text
  question answered 2026-07-12 · verification, neural-manifolds, recurrent-neural-networks, neuroscience, source-audit
• Verify the two Sadtler et al. (2014) 'Neural constraints on learning' quotes against the open-access full text
  question answered 2026-07-12 · verification, neural-manifolds, neuroscience, brain-computer-interface, source-audit
• Is the 'low-dimensional subspace that constrains adaptation' one shared mathematical object across neural manifolds and LLM intrinsic dimension — or three analogies that share a shape?
  question open 2026-07-12 · neural-manifolds, dimensionality, cross-domain-convergence, fine-tuning, learning
• Low-dimensional subspaces constrain adaptation in both brains and neural networks
  capture promoted Tier 1 2026-07-11 · neural-manifolds, dimensionality, learning, fine-tuning, LoRA