15.4. Pretraining word2vec — Dive into Deep Learning 1.0.0-beta0 documentation thumbnail
15.4. Pretraining word2vec — Dive into Deep Learning 1.0.0-beta0 documentation
d2l.ai
an embedding layer maps a token’s index to its feature vector. The weight of this layer is a matrix whose number of rows equals to the dictionary size (input_dim) and number of columns equals to the vector dimension for each token (output_dim)
1 Users
0 Comments
1 Highlights
0 Notes

Top Highlights

  • an embedding layer maps a token’s index to its feature vector. The weight of this layer is a matrix whose number of rows equals to the dictionary size (input_dim) and number of columns equals to the vector dimension for each token (output_dim)

Domain

Ready to highlight and find good content?

Glasp is a social web highlighter that people can highlight and organize quotes and thoughts from the web, and access other like-minded people’s learning.