3.1. Linear Regression — Dive into Deep Learning 1.0.3 documentation thumbnail
3.1. Linear Regression — Dive into Deep Learning 1.0.3 documentation
d2l.ai
Before we can go about searching for the best parameters (or model parameters) � and � , we will need two more things: (i) a measure of the quality of some given model; and (ii) a procedure for updating the model to improve its quality. (ii) iteratively sample random minibatches from the data, up
5 Users
0 Comments
157 Highlights
0 Notes

Top Highlights

  • Before we can go about searching for the best parameters (or model parameters) � and � , we will need two more things: (i) a measure of the quality of some given model; and (ii) a procedure for updating the model to improve its quality.
  • (ii) iteratively sample random minibatches from the data, updating the parameters in the direction of the negative gradient.
  • Regression
  • linear transformation of features via a weighted sum, combined with a translation via the added bias.
  • with the smallest error.

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.