This is a dedicated watch page for a single video.
A healthcare company is developing a supplementary diagnostic tool to detect if a person is suffering from depression by analyzing facial landmarks. The company has provided 20,000 image data for a Machine Learning Specialist to use in training the model. An early model evaluation reveals that as the number of epochs increases, the training error rate decreases exponentially which causes the model to generalize poorly. How can the Specialist resolve the problem?