A Data Odyssey

10:31

Build Class Activation Maps (CAMs) from Scratch with Python & PyTorch Hooks | Free XAI Course

10:11

Understanding Class Activation Maps (CAMs) for Deep Learning Interpretability | Free XAI Course

28:58

Implementing Guided Backpropagation from Scratch | PyTorch Hooks & Deep Learning Interpretability

11:21

Guided Backpropagation theory | FREE Explainable AI (XAI) Course with Python

18:10

Grad-CAM with Python | FREE XAI Course | L7 - Gradient-weighted Class Activation Mapping

13:37

Grad-CAM Explained | FREE XAI Course | L7 - Gradient-weighted Class Activation Mapping

5:16

Debugging a Pot Plant Detector | FREE Python Course | L1 - The Importance of XAI in Computer Vision

20:31

Applying Permutation Channel Importance (PCI) to a Remote Sensing Model | Python Tutorial

10:13

Explaining Computer Vision Models with PCI

26:19

Explaining Anomalies with Isolation Forest and SHAP | Python Tutorial

8:41

SHAP with CatBoostClassifier for Categorical Features | Python Tutorial

9:42

Applying LIME with Python | Local & Global Interpretations

8:36

An introduction to LIME for local interpretations | Intuition and Algorithm |

8:20

Friedman's H-statistic Python Tutorial | Artemis Package

15:06

Friedman's H-statistic for Analysing Interactions | Maths and Intuition

13:44

Accumulated Local Effect Plots (ALEs) | Explanation & Python Code

12:57

PDPs and ICE Plots | Python Code | scikit-learn Package

11:55

Partial Dependence (PDPs) and Individual Conditional Expectation (ICE) Plots | Intuition and Math

13:10

Permutation Feature Importance from Scratch | Explanation & Python Code

8:38

Model Agnostic Methods for XAI | Global v.s. Local | Permutation v.s. Surrogate Models

13:39

8 Plots for Explaining Linear Regression | Residuals, Weight, Effect & SHAP

15:55

Feature Selection using Hierarchical Clustering | Python Tutorial

16:16

8 Characteristics of a Good Machine Learning Feature | Predictive, Variety, Interpretability, Ethics

15:07

Interpretable Feature Engineering | How to Build Intuitive Machine Learning Features

9:32

Modelling Non-linear Relationships with Regression

13:23

Explaining Machine Learning to a Non-technical Audience

13:47

Get more out of Explainable AI (XAI): 10 Tips

15:05

The 6 Benefits of Explainable AI (XAI) | Improve accuracy, decrease harm and tell better stories

11:51

Introduction to Explainable AI (XAI) | Interpretable models, agnostic methods, counterfactuals

11:09

Data Science vs Science | Differences & Bridging the Gap

3:32

About the Channel and my Background | ML, XAI and Remote Sensing

12:59

SHAP for Binary and Multiclass Target Variables | Code and Explanations for Classification Problems

5:46

Introduction to Algorithm Fairness | Causes, Measuring & Preventing Unfairness in Machine Learning

5:26

SHAP Violin and Heatmap Plots | Interpretations and New Insights

9:01

Correcting Unfairness in Machine Learning | Pre-processing, In-processing, Post-processing

10:32

Definitions of Fairness in Machine Learning | Equal Opportunity, Equalized Odds & Disparate Impact

7:47

Exploratory Fairness Analysis | Quantifying Unfairness in Data

10:09

5 Reasons for Unfair Models | Proxy Variables, Unbalanced Samples & Negative Feedback Loops

9:03

Feature Engineering with Image Data | Aims, Techniques & Limitations

9:36

Image Augmentation for Deep Learning | Benefits, Techniques & Best Practices

7:07

Interpretable vs Explainable Machine Learning

6:35

4 Significant Limitations of SHAP

11:06

Shapley Values for Machine Learning

11:48

The mathematics behind Shapley Values

15:41

SHAP with Python (Code and Explanations)

7:07

SHAP values for beginners | What they mean and their applications

3:02

5 ways to use a Seaborn Heatmap

5:11

Data Exploration with PCA