Unverified50% confidenceFactExact time
A tensor is the core data structure in machine learning, and can be understood as a general term for multi-dimensional arrays: a scalar is a 0-dimensional tensor, a vector is 1-dimensional, a matrix is 2-dimensional, and higher dimensions are N-dimensional tensors.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEmbedding 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.76% similarUnverifiedAn 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.72% similarUnverifiedThe basic idea of embedding vectors is to map high-dimensional, discrete, or hard-to-compute objects into low-dimensional continuous dense vectors, so that semantically or visually similar objects are closer in vector space.67% similarUnverifiedSpectral clustering maps high-dimensional data to a low-dimensional spectral space by computing the eigenvectors of the graph Laplacian matrix, and then completes clustering with k-means.65% similarUnverifiedIn BERT, the word embedding matrix has dimensions V×d, where V is the vocabulary size and d is the hidden dimension 768, mapping discrete token IDs to dense real-valued vectors.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1019985API
curl https://kongchang.com/api/v1/knowledge/claims/1019985MCP
get_claim(id=1019985)