Unverified50% confidenceFactExact time
Linear bound propagation is a core technique in the formal verification of neural networks, used to compute safety bounds on neural network outputs with respect to input perturbations.
1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe essence of a neural network is linear regression: each neuron performs the linear computation WX+B, and a multi-layer network is a superposition of linear equations.76% similarUnverifiedLinear algebra is the computational language of forward and backward propagation in neural networks, where matrix multiplication corresponds to the linear transformation of fully connected layers and eigenvalue decomposition corresponds to PCA dimensionality reduction.73% similarUnverified线性表征假说认为神经网络中的概念以线性方向(方向向量)的形式存储在激活空间中73% similarVerifiedThe forward propagation of a neural network is essentially matrix multiplication.72% similarUnverifiedThe phenomenon that optimization of over-parameterized neural networks easily converges to good solutions can be explained by Neural Tangent Kernel theory71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1153680API
curl https://kongchang.com/api/v1/knowledge/claims/1153680MCP
get_claim(id=1153680)