Recurrent neural network in 3D
Unroll a sequence and trace a state reused across time steps. Explore the 3D model, inspect its parts and learn with guided explanations. Free on Atlas.
What you can learn
Unroll a sequence and trace a state reused across time steps.
Keep the time order.
Follow the carried information.
Distinguish gates from physical switches.
Try an investigation
Trace sequence inputs toward gru gate calculation. Which intermediate operations or assemblies are essential, and which assumptions are simplified by this diagram?
Check your understanding
Unrolled cells typically reuse…
The same learned parameters. The same learned parameters. The exhibit shows computational roles and dependencies; it does not contain trained parameters or run inference.
The recurrent connection carries…
A hidden state. A hidden state. The exhibit shows computational roles and dependencies; it does not contain trained parameters or run inference.
A learned gate is…
A vector-valued mathematical operation. A vector-valued mathematical operation. The exhibit shows computational roles and dependencies; it does not contain trained parameters or run inference.
Sources and model scope
A three-dimensional computational diagram, not physical hardware or a running trained model. Displayed widths, node counts and example values are illustrative. Select named stages to trace information flow. The separate upper study rail contains deterministic worked examples, with values on every selectable cell.