Asosiy kontentga oʻtish
AkademIndex

Mahsulotlar

Ishlab chiquvchilar uchun

AkademBasetez oradaEkotizim uchun ochiq API
Lotin
Oʻzbek
Bob

Explainable AI (XAI) for Classical ML and LLMs

Brijendra GuptaErgashev Nuriddin GayratovichKarshi State Technical University, Karshi, UzbekistanErkin KholiyarovTermez University of Economics and Service, Termez, UzbekistanNazirjon RajabovAlfraganus University, Tashkent, UzbekistanGulkhayo OtajonovaJumayev AkbarTashkent State University of Economics, UzbekistanSultonmakhmud PolvanovUrgench State University Named After Abu Rayhan Biruni, Uzbekistan
ABI

Annotatsiya

Explainable Artificial Intelligence (XAI) constitutes a foundational pillar of responsible AI deployment, addressing the opacity of data-driven decision systems by making their internal logic transparent, auditable, and contestable. This chapter provides a systematic account of explainability and interpretability across the full spectrum of AI models — from classical supervised learning algorithms such as decision trees, support vector machines, and gradient-boosted ensembles to contemporary Large Language Models (LLMs) built on transformer architectures. Beginning with a structured taxonomy of XAI properties — scope, stage, model-dependency, and output type — the chapter critically examines canonical explanation methods including SHAP, LIME, attention visualization, mechanistic circuit analysis, and counterfactual generation.

Mavzular

Identifikatorlar

Iqtiboslar va manbalar

0 ta iqtibos0 ta foydalanilgan manba
Koʻrsatkichlar — AkademScholar · Tez orada