Deep Learning xAI

Focuses on explainability in the context of neural networks. You will explore techniques designed for deep models and develop skills to interpret complex architectures.

0 Rating
0 Reviews
1 Students Enrolled

Suggested citation

Misheva, Branka Hadji (2025). Deep Learning xAI. Q2 ecosystem. Available at https://quantinar.com/course/943/deep-learning-xa or http://dx.doi.org/10.24818/IDA-CL/2025.96.

@misc{misheva2025, author = {Misheva, Branka Hadji}, title = {Deep Learning xAI}, year = {2025}, howpublished = {Q2 ecosystem}, doi = {http://dx.doi.org/10.24818/IDA-CL/2025.96.}, url = {https://quantinar.com/course/943/deep-learning-xa} }
Wishlist

Free

Enroll Now

Tags:

Courselet Content

1 components

	Deep Learning xAI (pdf)	2.74 M

Requirements

1) Foundations in Machine Learning – understanding of supervised learning, model training, overfitting, feature importance. 2) Mathematical Background – basic linear algebra, probability, and statistics (enough to follow Shapley values and regression concepts). 3) Programming Skills – ability to work with Python (libraries such as scikit-learn, XGBoost, SHAP, LIME).

General Overview

Description

This session focuses on the unique challenges of explaining neural networks, which are often viewed as “black boxes” due to their layered, nonlinear structure. You will explore a range of techniques specifically designed for deep models, including saliency maps and integrated gradients. We will discuss how these methods trace predictions back through the network to highlight influential features, and how they differ in terms of interpretability, faithfulness, and computational cost.