{"type":"link","version":"1.0","title":"Randomly reloading a saved recurrent state during training lets a model extrapolate to far more update steps than it ever saw","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/stochastic-state-reload-extrapolates-recurrence-depth","thumbnail_url":"https://ai-arch.pages.dev/android-chrome-512x512.png","thumbnail_width":512,"thumbnail_height":512}