Models Got Talent: Identifying High Performing Wearable Human Activity Recognition Models Without Training
cs.LG, cs.AI
Submitted: 2025-11-08
Updated: 2026-09-25
Terminology
Sources
- Evaluating the Search Phase of Neural Architecture Search
- DARTS: Differentiable Architecture Search
- Zero-Cost Proxies for Lightweight NAS
- Neural Architecture Search with Reinforcement Learning
- Neural Architecture Search without Training
- NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies
- An Evaluation of Zero-Cost Proxies -- from Neural Architecture Performance to Model Robustness
- SNIP: Single-shot Network Pruning based on Connection Sensitivity
- Picking Winning Tickets Before Training by Preserving Gradient Flow
- Pruning neural networks without any data by iteratively conserving synaptic flow
- BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget
- Adam: A Method for Stochastic Optimization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks