Unverified60% confidenceFactExact time
The reverse SDE of a diffusion process can be expressed as dX_t = [f(X_t,t) - g(t)²∇log p_t(X_t)]dt + g(t)dW̄_t.
2
Sources
60%
Confidence
Long-term
Relevance
8/13/2026
First Seen
Sources
Related Claims
UnverifiedOU过程具有均值回归性质，其数学形式为 dXt = -αXt dt + σ dWt，通过适当设置参数任意初始分布会在有限时间内指数级收敛到标准高斯分布69% similarUnverifiedThe forward diffusion process of a diffusion model can be described using a Markov chain: q(x_t|x_{t-1}) = N(x_t; √(1-β_t)x_{t-1}, β_tI).69% similarUnverifiedIn the DDPM reverse process, the mean μ_θ is expressed as μ_θ(x_t, t) = (1/√α_t) · (x_t - (β_t / √(1 - ᾱ_t)) · ε_θ(x_t, t)), where ε_θ is the neural network to be trained.66% similarUnverifiedThe forward propagation process of logistic regression is: linear combination z = w·x + b, activated through sigmoid as ŷ = 1/(1+e^(-z)), followed by cross-entropy loss calculation.65% similarUnverifiedThe continuous form of a state space model is h'(t) = A·h(t) + B·x(t), with output y(t) = C·h(t) + D·x(t); after discretization it processes a sequence of length n with O(n) complexity.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/741095API
curl https://kongchang.com/api/v1/knowledge/claims/741095MCP
get_claim(id=741095)