🏠 Home
Benchmark
📊 Tutti i benchmark 🦖 Dinosauro v1 🦖 Dinosauro v2 ✅ App To-Do List 🎨 Pagine libere creative 🎯 FSACB - Ultimate Showcase 🌍 Benchmark traduzione
Modelli
🏆 Top 10 modelli 🆓 Modelli gratuiti 📋 Tutti i modelli ⚙️ Kilo Code
Risorse
💬 Libreria di prompt 📖 Glossario IA 🔗 Link utili

Glossario IA

Il dizionario completo dell'Intelligenza Artificiale

162
categorie
2.032
sottocategorie
23.060
termini
📂
sottocategorie

Local Interpretable Model-agnostic Explanations (LIME)

Explanation techniques that analyze individual predictions to understand how a model makes a specific decision.

9 termini
📂
sottocategorie

SHAP methods (SHapley Additive exPlanations)

Game theory-based approach to quantify the impact of each feature on model predictions.

8 termini
📂
sottocategorie

Feature Analysis

Systematic study of the importance, relevance, and impact of input variables on model predictions.

0 termini
📂
sottocategorie

Model Visualization

A set of graphical techniques for visually representing the internal behavior and decisions of AI models.

4 termini
📂
sottocategorie

Counterfactual Analysis

Generating alternative scenarios to understand which minimal changes to inputs would change the model's prediction.

12 termini
📂
sottocategorie

Interpretation Rules

Extraction of simple and understandable logical rules from complex models such as neural networks.

9 termini
📂
sottocategorie

Post-hoc interpretability

Methods applied after training to explain the decisions of initially non-interpretable models.

3 termini
📂
sottocategorie

Interpretability by design

Approaches where transparency is integrated from the model's design, creating naturally explainable algorithms.

12 termini
📂
sottocategorie

Causal Explanations

Analysis of cause-and-effect relationships in model decisions to go beyond simple correlations.

7 termini
📂
sottocategorie

Algorithmic Bias Analysis

Detection, quantification and explanation of systematic biases in AI model predictions.

7 termini
📂
sottocategorie

Explanation fidelity metrics

Set of measures to evaluate the quality and accuracy of explanations generated by interpretability techniques.

13 termini
📂
sottocategorie

Interpretable decision trees

Tree structures specifically designed to provide transparent and easily understandable decisions.

5 termini
📂
sottocategorie

Saliency Maps

Visualization techniques that highlight the most influential regions or features in the input data.

7 termini
📂
sottocategorie

Multimodal explanations

Interpretation approaches tailored to models processing multiple data types simultaneously (text, image, audio).

13 termini
📂
sottocategorie

Transparency audit

Systematic and independent evaluation of the transparency, fairness, and reliability of AI models.

6 termini
🔍

Nessun risultato trovato