ConceptAI & ML
Batch normalization limitations
Drawbacks of batch normalization in deep learning include creating a strong dependency on batch size, behaving differently at train and test times, and complicating distributed computing.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Batch normalization1Deep learning training1
Lecturers
1Connections
2The lectures that define it or assume it, and the concepts next to it.