Knowledge Graph — Coursera Notes › Academic disciplines › Information Technology / Computer Science › Artificial Intelligence › Deep Learning › Model Training › Model Training Monitoring

Training Loss

concept · part of Model Training Monitoring

Training loss is a measure of how well the model is learning from the training dataset. It represents the difference between the predicted output and the actual output during training. A decreasing training loss indicates that the model is improving in its ability to predict correct values from the training data.

This is the text view of an interactive 3D knowledge graph — open this page with JavaScript enabled to explore it visually.