Silico Tool Decodes AI Models to Detect Parkinson's Gait

Researchers utilized the Silico tool with sparse autoencoders to successfully reverse-engineer human motion AI models, confirming their effectiveness in detecting Parkinsonian gait and visualizing the underlying predictive mechanisms.

2026-08-05 ~ 2026-08-05 · 4 related posts

• Probing Parkinson's Gait Models with SAEs: Stride Amplitude Drives Severity Predictions — mathildepapillo · 2026-08-05
• Deciphering Human Motion AI Models Using Sparse Autoencoders (SAEs) — mathildepapillo · 2026-08-05
• Silico: Using Motion AI Models to Detect Parkinson's Gait — ninamiolane · 2026-08-05
• How AI Detects Parkinson's Gait: Silico Tool Visualizes Model Predictions — mathildepapillo · 2026-08-05