backward pass
The computational phase in backpropagation where error signals propagate backward from output to input layers, calculating gradients for weight updates
As defined in The Brain’s Learning Algorithm Isn’t Backpropagation
Where it comes up · 1
Most important claims · 1 of 1Search all claims for “backward pass” →
- Backpropagation requires discontinuous processing where neurons must freeze their feedforward activity values while error signals flow backward, requiring the brain to pause information processing for hundreds of milliseconds before updating connections.The Brain’s Learning Algorithm Isn’t Backpropagation