Applied Deep Learning 2025 - Lecture 10 - Explainable AI

Alexander Pacha · Beginner ·🧬 Deep Learning ·7mo ago

About this lesson

It's great that we can train machine learning models, but what if they don't work as we expect them to? How can we know that our trained models are basing their decisions on the right reasons, and are not just guessing, or even worse, are biased from our training dataset which makes the model seem to work fine, but actually doing horrible in practice? In this lecture, we're exploring a couple of methods for getting at least a few explanations about what's going on inside of a model. Complete Playlist: https://www.youtube.com/watch?v=vlTnIjhhmzA&list=PLNsFwZQ_pkE8H1o874cZbiwnNRJ6hCDJI 00:00:00 - Start 00:00:53 - Why Trust a Model? 00:03:00 - The Blackbox Problem 00:03:48 - Interpretability vs. Explainability 00:12:11 - Goals of Explainable AI 00:17:21 - Explainability vs. Accuracy 00:18:40 - Taxonomy of XAI 00:25:04 - Saliency Maps 00:32:15 - More visualization methods 00:33:15 - Local Interpretable Model-agnostic Explanations (LIME) 00:39:29 - Randomized Input Sampling for Explanations (RISE) 00:41:41 - XAI in Reinforcement Learning 00:43:42 - Quantized Bottleneck Insertions 00:47:40 - Understanding GANs 00:55:10 - Shapley Additive Explanations (SHAP) 01:03:04 - Summary == Literature == 1. Molnar, Interpretable Machine Learning. 2019 2. Arrieta et al., Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI. 2019 3. Petsiuk et al., RISE: Randomized Input Sampling for Explaination of Black-box Models. 2018 4. Bau et al., GAN Dissection: Visualizing and Understanding Generative Adversarial Networks. 2018 5. Koul et al., Learning Finite State Representations of Recurrent Policy Networks. 2018 6. Ribeiro et al. “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. 2016 7. Sarkar. Model Interpretation Strategies. 2018. 8. Lundberg et al. A Unified Approach to Interpreting Model Predictions. 2017 9. Tjoa et al. A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI. 2019

Original Description

It's great that we can train machine learning models, but what if they don't work as we expect them to? How can we know that our trained models are basing their decisions on the right reasons, and are not just guessing, or even worse, are biased from our training dataset which makes the model seem to work fine, but actually doing horrible in practice? In this lecture, we're exploring a couple of methods for getting at least a few explanations about what's going on inside of a model. Complete Playlist: https://www.youtube.com/watch?v=vlTnIjhhmzA&list=PLNsFwZQ_pkE8H1o874cZbiwnNRJ6hCDJI 00:00:00 - Start 00:00:53 - Why Trust a Model? 00:03:00 - The Blackbox Problem 00:03:48 - Interpretability vs. Explainability 00:12:11 - Goals of Explainable AI 00:17:21 - Explainability vs. Accuracy 00:18:40 - Taxonomy of XAI 00:25:04 - Saliency Maps 00:32:15 - More visualization methods 00:33:15 - Local Interpretable Model-agnostic Explanations (LIME) 00:39:29 - Randomized Input Sampling for Explanations (RISE) 00:41:41 - XAI in Reinforcement Learning 00:43:42 - Quantized Bottleneck Insertions 00:47:40 - Understanding GANs 00:55:10 - Shapley Additive Explanations (SHAP) 01:03:04 - Summary == Literature == 1. Molnar, Interpretable Machine Learning. 2019 2. Arrieta et al., Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI. 2019 3. Petsiuk et al., RISE: Randomized Input Sampling for Explaination of Black-box Models. 2018 4. Bau et al., GAN Dissection: Visualizing and Understanding Generative Adversarial Networks. 2018 5. Koul et al., Learning Finite State Representations of Recurrent Policy Networks. 2018 6. Ribeiro et al. “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. 2016 7. Sarkar. Model Interpretation Strategies. 2018. 8. Lundberg et al. A Unified Approach to Interpreting Model Predictions. 2017 9. Tjoa et al. A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI. 2019
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related Reads

Chapters (16)

Start
0:53 Why Trust a Model?
3:00 The Blackbox Problem
3:48 Interpretability vs. Explainability
12:11 Goals of Explainable AI
17:21 Explainability vs. Accuracy
18:40 Taxonomy of XAI
25:04 Saliency Maps
32:15 More visualization methods
33:15 Local Interpretable Model-agnostic Explanations (LIME)
39:29 Randomized Input Sampling for Explanations (RISE)
41:41 XAI in Reinforcement Learning
43:42 Quantized Bottleneck Insertions
47:40 Understanding GANs
55:10 Shapley Additive Explanations (SHAP)
1:03:04 Summary
Up next
RNNs Explained in 60 Seconds #ai #coding #machinelearning
Ascent
Watch →