liveBook · Manning

Learning signal

As explained in Building Specialized AI Systems

A training signal is information in labeled examples that indicates how a model should adjust its behavior during learning.

A learning signal turns raw data into directional instruction by pairing each input with an output—the intended answer. In supervised fine-tuning, it shows the model what behavior to learn. section 2.4.2

Useful signals are precise, consistent, and intentional. Ambiguous or conflicting labels teach the model those weaknesses, so annotation guidelines and standardization matter as much as model architecture. section 2.4.2

Choose the output form according to the intended use:

  • Use compact labels such as "category: utilities" for transaction classification. section 2.4.2
  • Use complete sentences when the model must produce readable client summaries. section 2.4.2
  • Use machine-readable formats such as JSON when downstream systems require structured output. section 2.4.2

How Building Specialized AI Systems covers it

How deep it goes
Explains construction, quality requirements, and output choices, but does not descend into model internals.
Examples
Uses suspicious-versus-legitimate transactions, utility categories, client summaries, and JSON labels as concrete examples.
What it assumes
Assumes collected, cleaned, and structured data, while explaining how to add responses through labeling.
What you can do after
Apply labeling choices to create consistent supervised fine-tuning examples and select suitable output formats.
How it connects
Connects labeling with annotation guidelines, evaluation metrics, post-processing, classification, and structured output.

Also explained in

Compare how 4 books explain learning signal →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Building Specialized AI Systems. The section links point to the parts of the book it draws on.