Explainable AI

Course Code:B23AM4107

Course Outcomes :

CO1:Understand the fundamental concepts of Explainable AI (XAI) and its role in interpreting machine learning model predictions.

CO2:Use interpretable modeling techniques such as linear models, decision trees, rule-based systems, and neural network-based approaches to explain and analyze model predictions.

CO3:Apply various Explainable AI methods such as PDP, ICE, LIME, SHAP, saliency maps, and integrated gradients to interpret and analyze linear, nonlinear, and deep learning models

CO4:Apply evaluation techniques and metrics used to assess the effectiveness, trustworthiness, and ethical considerations of XAI methods.

CO5:Apply Explainable AI techniques in diverse application domains such as healthcare, finance, autonomous systems, time series forecasting, natural language processing, and computer vision to interpret model outcomes.

Textbooks Link: Munn, Michael, and David Pitman. Explainable AI for practitioners. " O'Reilly Media, Inc.", 2022.

https://christophm.github.io/interpretable-ml-book/

UNIT-1

Introduction to Explainable AI (XAI): Motivations for XAI, Importance of Interpretability and Transparency techniques for XAI, Model-specific interpretability methods (e.g., decision trees, rule-based systems), Model-agnostic interpretability methods (e.g., LIME, SHAP), Post-hoc explanation techniques (e.g., feature importance, counterfactual explanation).

PPT MATERIAL

UNIT-2

Interpretable Models:

Linear Models, Decision Trees and Rule-based systems, Symbolic AI approaches, Interpretable Neural Networks, Sparse Neural Networks, Attention mechanisms, Layer-wise relevance propagation (LRP).

PPT MATERIAL

UNIT-3

Methods for Explainable AI:

Partial Dependence Plot (PDP), Conformal Prediction, Individual Conditional Expectation (ICE), Feature Importance, Saliency Maps, Local Interpretable Model Agnostic Explanations (LIME), SHAP, Integrated Gradient (IG), Explainability for Linear Models, Non-Linear Models and Deep Learning Models.

PPT MATERIAL

UNIT-4

Evaluation of XAI Methods:

Quantitative metrics for interpretability, Human-centric evaluation methods, Ethical and Societal Implications of XAIB, Trust and accountability in AI systems, Regulatory considerations.

PPT MATERIAL

UNIT-5

Applications of XAI:

Healthcare (e.g., Medical diagnosis, personalized treatment), Finance (e.g., credit scoring, fraud detection), Autonomous systems (e.g., self-driving cars, drones), Explainability in Time Series forecasting, Natural Language Processing and Computer Vision.

PPT MATERIAL

Google Sites

Report abuse