Interpretable AI : building explainable machine learning systems / Ajay Thampi

Part 1. Interpretability basics -- 1. Introduction -- 2. White-box models -- Part 2. Interpreting model processing -- 3. Model-agnostic methods: Global interpretability -- 4. Model-agnostic methods: Local interpretability -- 5. Saliency mapping -- Part 3. Interpreting model representations -- 6. Understanding layers and units -- 7. Understanding semantic similarity -- Part 4. Fairness and bias -- 8. Fairness and mitigating bias -- 9. Path to explainable AI -- Appendix A. Getting set up -- Appendix B. PyTorch.

Interpretable AI teaches you to identify the patterns your model has learned and why it produces its results. As you read, you’ll pick up algorithm-specific approaches, like interpreting regression and generalized additive models, along with tips to improve performance during training. You’ll also explore methods for interpreting complex deep learning models where some processes are not easily observable. AI transparency is a fast-moving field, and this book simplifies cutting-edge research into practical methods you can implement with Python. What's Inside: Techniques for interpreting AI models. Counteract errors from bias, data leakage, and concept drift. Measuring fairness and mitigating bias. Building GDPR-compliant AI systems. For data scientists and engineers familiar with Python and machine learning.

COBERTURA BIBLIOGRAFICA:
INF473
Asignatura : Introducción a la inteligencia artificial explicable

Última actualización 13 de noviembre 2023