Unverified50% confidenceFactExact time
Reverse mode automatic differentiation can obtain gradients of the loss with respect to all parameters in a single backward pass, with complexity only a constant multiple of the forward computation (typically 2–4×).
1
Sources
50%
Confidence
Long-term
Relevance
9/9/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedGradient descent iteratively adjusts weights in the opposite direction of the loss function's gradient, causing the prediction error to converge progressively.73% similarUnverifiedWhen the factors multiplied by the chain rule are continuously less than 1, gradients decay exponentially (vanishing); when they are continuously greater than 1, gradients grow exponentially (exploding).70% similarUnverifiedIn autoregressive prediction, errors at each step accumulate into the next, causing long-range predictions to degrade rapidly.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/885580API
curl https://kongchang.com/api/v1/knowledge/claims/885580MCP
get_claim(id=885580)