Unverified50% confidenceFactExact time
poly核将原始d维输入隐式映射到O(n^d)维特征空间，维度随degree指数级增长，计算代价急剧膨胀
1
Sources
50%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
Related Claims
UnverifiedAn embedding layer is essentially a learnable matrix of size V×D (where V is the vocabulary size and D is the embedding dimension) that looks up the corresponding row vector when given a token ID.66% similarUnverifiedEmbedding vectors are essentially high-dimensional numerical vectors output by intermediate layers of a neural network, typically having hundreds to thousands of dimensions, and represent the coordinates of raw input data in a learned semantic space.64% similarUnverifiedDepth estimation, which recovers three-dimensional spatial information from two-dimensional images, is an ill-posed problem because there are infinitely many possible solutions for the mapping from 2D to 3D62% similarUnverified标准 Scaled Dot-Product Attention 中 Q 与 K 做矩阵乘法得到 n×n 注意力分数矩阵，计算量为 O(n²·d)60% similarUnverifiedFrom PCA dimensionality reduction to the attention mechanism in Transformers, matrix operations and vector space transformations are fundamental.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/564628API
curl https://kongchang.com/api/v1/knowledge/claims/564628MCP
get_claim(id=564628)