This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse
This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse explores Adaptive Manifold Prototypes (AMP) improves classification accuracy and interpretability by representing class prototypes as orthonormal bases on the Stiefel manifold, preventing prototype collapse.. Commercial viability score: 7/10 in Interpretable Machine Learning.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $9K - $13K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Builds On ThisNeural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm ThresholdViability: 3.0
- Builds On ThisAvoiding Premature Collapse: Adaptive Annealing for Entropy-Regularized Structural InferenceViability: 6.0
- Builds On ThisDiagnosing Generalization Failures from Representational Geometry MarkersViability: 5.0
- Builds On ThisDeep Neural Regression CollapseViability: 3.0
- Builds On ThisAnatomy of Capability Emergence: Scale-Invariant Representation Collapse and Top-Down Reorganization in Neural Networks