Artificial neural network in 3D
Inspect weighted connections, activations and a prediction layer. Explore the 3D model, inspect its parts and learn with guided explanations. Free on Atlas.
What you can learn
Inspect weighted connections, activations and a prediction layer.
Start with the represented variables.
Combine values, then apply a nonlinearity.
Interpret the task-specific output.
Try an investigation
Trace input features toward weighted sum and relu. Which intermediate operations or assemblies are essential, and which assumptions are simplified by this diagram?
Check your understanding
A hidden unit combines…
Weighted inputs and a bias. Weighted inputs and a bias. The exhibit shows computational roles and dependencies; it does not contain trained parameters or run inference.
Hidden activations usually include…
A nonlinear transformation. A nonlinear transformation. The exhibit shows computational roles and dependencies; it does not contain trained parameters or run inference.
Training adjusts parameters using…
An objective and its derivatives. An objective and its derivatives. 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.