Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
Valutare un modello di machine learning (ML) in modo responsabile richiede più del semplice calcolo delle metriche di perdita complessive. Prima di mettere un modello in produzione,
è fondamentale eseguire la revisione dei dati di addestramento e valutare le previsioni per verificare la presenza di bias.
Questo modulo esamina i diversi tipi di bias umani che possono manifestarsi nei
dati di addestramento. Fornisce quindi strategie per identificarli e mitigarli, nonché per valutare le prestazioni del modello tenendo conto dell'equità.
[[["Facile da capire","easyToUnderstand","thumb-up"],["Il problema è stato risolto","solvedMyProblem","thumb-up"],["Altra","otherUp","thumb-up"]],[["Mancano le informazioni di cui ho bisogno","missingTheInformationINeed","thumb-down"],["Troppo complicato/troppi passaggi","tooComplicatedTooManySteps","thumb-down"],["Obsoleti","outOfDate","thumb-down"],["Problema di traduzione","translationIssue","thumb-down"],["Problema relativo a esempi/codice","samplesCodeIssue","thumb-down"],["Altra","otherDown","thumb-down"]],["Ultimo aggiornamento 2025-07-27 UTC."],[[["\u003cp\u003eThis module focuses on identifying and mitigating human biases that can negatively impact machine learning models.\u003c/p\u003e\n"],["\u003cp\u003eYou'll learn how to proactively examine data for potential bias before model training and how to evaluate your model's predictions for fairness.\u003c/p\u003e\n"],["\u003cp\u003eThe module explores various types of human biases that can unintentionally be replicated by machine learning algorithms, emphasizing responsible AI development.\u003c/p\u003e\n"],["\u003cp\u003eIt builds upon foundational machine learning knowledge, including linear and logistic regression, classification, and handling numerical and categorical data.\u003c/p\u003e\n"]]],[],null,["# Fairness\n\n| **Estimated module length:** 110 minutes\n\nEvaluating a machine learning model (ML) responsibly requires doing more than\njust calculating overall loss metrics. Before putting a model into production,\nit's critical to audit training data and evaluate predictions for\n[bias](/machine-learning/glossary#bias-ethicsfairness).\n\nThis module looks at different types of human biases that can manifest in\ntraining data. It then provides strategies to identify and mitigate them,\nand then evaluate model performance with fairness in mind.\n| **Learning objectives**\n|\n| - Become aware of common human biases that can inadvertently be reproduced by ML algorithms.\n| - Proactively explore data to identify sources of bias before training a model.\n| - Evaluate model predictions for bias.\n| **Prerequisites:**\n|\n| This module assumes you are familiar with the concepts covered in the\n| following modules:\n|\n| - [Introduction to Machine Learning](/machine-learning/intro-to-ml)\n| - [Linear regression](/machine-learning/crash-course/linear-regression)\n| - [Logistic regression](/machine-learning/crash-course/logistic-regression)\n| - [Classification](/machine-learning/crash-course/classification)\n| - [Working with numerical data](/machine-learning/crash-course/numerical-data)\n| - [Working with categorical data](/machine-learning/crash-course/categorical-data)\n- [Datasets, generalization, and overfitting](/machine-learning/crash-course/overfitting) \n| **Key terms:**\n|\n| - [Bias (ethics/fairness)](/machine-learning/glossary#bias-ethicsfairness)\n- [Model](/machine-learning/glossary#model) \n[Help Center](https://support.google.com/machinelearningeducation)"]]
