Feature Scaling in Machine Learning and Deep Learning

When training machine learning and deep learning models, preprocessing and scaling features is crucial for model convergence and performance. Two common techniques are the StandardScaler and MinMaxScaler. Let’s dive into their details, compare their strengths, and see how they fit into the world of deep learning and transformers.

StandardScaler vs. MinMaxScaler


  • Definition: Standardizes features by removing the mean and scaling to unit variance.
  • Formula: z = (X - mean(X)) / std(X)
  • Characteristics: After applying, data will have a mean of 0 and a standard deviation of 1.


  • Definition: Scales features by transforming them into a given range, typically between [0, 1].
  • Formula: X_scaled = (X - min(X)) / (max(X) - min(X))
  • Characteristics: Data values will reside between the range 0 and 1.

Which is Better for Deep Learning and Transformers?

Deep learning introduces additional complexities that make the choice of scaler less clear-cut. Here are key points to consider:

Batch Normalization

  • Deep models, particularly CNNs, use batch normalization layers to stabilize training, rendering the initial scaling method less crucial. However, transformers typically use layer normalization instead.

Activation Functions

  • Activation functions like ReLU, sigmoid, and tanh have specific behaviors and ranges. Standardizing input features can ensure that more values fall within their active regions, aiding learning.

Empirical Performance

  • Both scalers can be effective. However, for deep learning applications, there’s a slight preference towards StandardScaler, or simply making data zero-centered.

Attention Mechanisms in Transformers

  • Attention mechanisms in transformers compute dot products between vectors. If these vectors have very large or small values, the resulting dot products can be unstable, thus some normalization is beneficial.


  • In NLP tasks with transformers, word embeddings like word2vec or BERT are often used. These embeddings are already on a consistent scale, making additional scaling sometimes unnecessary.


While scaling or normalization is crucial for model performance, the choice between StandardScaler and MinMaxScaler in deep learning isn’t rigid. Experimentation remains the gold standard to see what works best for specific problems and datasets.

Author: robot learner
Reprint policy: All articles in this blog are used except for special statements CC BY 4.0 reprint policy. If reproduced, please indicate source robot learner !