Retraining a spam detection model to handle new edge cases

Learn how to retrain your comment spam classification model to account for the instances it does not classify correctly. Here we learn how our previously chosen model fails with certain edge cases, what we can do to reduce errors, and then how to retrain the model with our new edge case data via Model Maker which can be exported to the TensorFlow.js format for use on the web.

View more from this path: Web ML learning path - Go further with comment spam detection → https://goo.gle/2QwziU8
Prerequisite learning path: Web ML - Get started with comment-spam detection → https://goo.gle/3tVP8oS

TensorFlow.js website → https://goo.gle/2XLhMe0

Get inspired by #MadeWithTFJS projects → http://goo.gle/made-with-tfjs
Subscribe to TensorFlow → https://goo.gle/TensorFlow

#MadeWithTFJS #GoogleIO #WebML #TensorFlowJS #TensorFlow

Видео Retraining a spam detection model to handle new edge cases канала TensorFlow