Skip to content

Latest commit

 

History

History
7 lines (4 loc) · 347 Bytes

README.md

File metadata and controls

7 lines (4 loc) · 347 Bytes

RankNet

An implementation of RankNet using TensorFlow and Keras.

This sample considers a 3 dimensional input vector and constructs a 3 layer neural network trained over 20 epochs with NDCG as the measure of ranking quality.

Courtesy: Learning to Rank using Gradient Descent