Computation Graph
A graph structure in deep learning frameworks that represents a model's computation, where nodes correspond to operators and edges indicate the direction of tensor flow, used for forward and backward propagation.
Timeline (last 90 days)
Automatic differentiation dynamically constructs a directed acyclic graph (computation graph) by recording each operation and its inputs during every forward computation, and during backpropagation it traverses the graph's reverse edges, sequentially invoking each operation's local gradient function to accumulate gradients via the chain rule
All Facts (2)
Modern deep learning frameworks use automatic differentiation to build a computation graph during forward propagation and automatically compute gradients in reverse along the graph during backpropagation.
60%UnverifiedAutomatic differentiation dynamically constructs a directed acyclic graph (computation graph) by recording each operation and its inputs during every forward computation, and during backpropagation it traverses the graph's reverse edges, sequentially invoking each operation's local gradient function to accumulate gradients via the chain rule
50%