You need to implement a scaling strategy for the local penalty detection data. Which normalization type should you use?

The correct answer is C. Batch. Batch normalization is used when the entire dataset is available locally and can be processed all at once. It computes normalization statistics (mean, standard deviation) across the full batch of data, making it ideal for local, static datasets like penalty detection data…

Design and prepare a machine learning solution

Question

You need to implement a scaling strategy for the local penalty detection data. Which normalization type should you use?

Options

AStreaming
BWeight
CBatch
DCosine

How the community answered

(26 responses)

A
8% (2)
B
4% (1)
C
81% (21)
D
8% (2)

Explanation

Batch normalization is used when the entire dataset is available locally and can be processed all at once. It computes normalization statistics (mean, standard deviation) across the full batch of data, making it ideal for local, static datasets like penalty detection data. Streaming normalization is designed for real-time/incremental data that arrives continuously. Cosine normalization is a similarity metric, not a scaling technique. Weight normalization is used in neural network layers, not for scaling input data features.

Topics

#Data Preprocessing#Normalization#Batch Normalization#Scaling

Community Discussion

No community discussion yet for this question.

Full DP-100 Practice