Build Class Activation Maps (CAMs) from Scratch with Python & PyTorch Hooks | Free XAI Course
A Data Odyssey
Build Class Activation Maps (CAMs) from Scratch with Python & PyTorch Hooks | Free XAI Course
10:31
Understanding Class Activation Maps (CAMs) for Deep Learning Interpretability | Free XAI Course
A Data Odyssey
Understanding Class Activation Maps (CAMs) for Deep Learning Interpretability | Free XAI Course
10:11
Implementing Guided Backpropagation from Scratch | PyTorch Hooks & Deep Learning Interpretability
A Data Odyssey
Implementing Guided Backpropagation from Scratch | PyTorch Hooks & Deep Learning Interpretability
28:58
Guided Backpropagation theory | FREE Explainable AI (XAI) Course with Python
A Data Odyssey
Guided Backpropagation theory | FREE Explainable AI (XAI) Course with Python
11:21
Grad-CAM with Python | FREE XAI Course | L7 - Gradient-weighted Class Activation Mapping
A Data Odyssey
Grad-CAM with Python | FREE XAI Course | L7 - Gradient-weighted Class Activation Mapping
18:10
Grad-CAM Explained | FREE XAI Course | L7 - Gradient-weighted Class Activation Mapping
A Data Odyssey
Grad-CAM Explained | FREE XAI Course | L7 - Gradient-weighted Class Activation Mapping
13:37
Debugging a Pot Plant Detector | FREE Python Course | L1 - The Importance of XAI in Computer Vision
A Data Odyssey
Debugging a Pot Plant Detector | FREE Python Course | L1 - The Importance of XAI in Computer Vision
5:16
Applying Permutation Channel Importance (PCI) to a Remote Sensing Model | Python Tutorial
A Data Odyssey
Applying Permutation Channel Importance (PCI) to a Remote Sensing Model | Python Tutorial
20:31
Explaining Computer Vision Models with PCI
A Data Odyssey
Explaining Computer Vision Models with PCI
10:13
Explaining Anomalies with Isolation Forest and SHAP | Python Tutorial
A Data Odyssey
Explaining Anomalies with Isolation Forest and SHAP | Python Tutorial
26:19
SHAP with CatBoostClassifier for Categorical Features | Python Tutorial
A Data Odyssey
SHAP with CatBoostClassifier for Categorical Features | Python Tutorial
8:41
Applying LIME with Python | Local & Global Interpretations
A Data Odyssey
Applying LIME with Python | Local & Global Interpretations
9:42
An introduction to LIME for local interpretations | Intuition and Algorithm |
A Data Odyssey
An introduction to LIME for local interpretations | Intuition and Algorithm |
8:36
Friedman's H-statistic Python Tutorial | Artemis Package
A Data Odyssey
Friedman's H-statistic Python Tutorial | Artemis Package
8:20
Friedman's H-statistic for Analysing Interactions | Maths and Intuition
A Data Odyssey
Friedman's H-statistic for Analysing Interactions | Maths and Intuition
15:06
Accumulated Local Effect Plots (ALEs) | Explanation & Python Code
A Data Odyssey
Accumulated Local Effect Plots (ALEs) | Explanation & Python Code
13:44
PDPs and ICE Plots | Python Code | scikit-learn Package
A Data Odyssey
PDPs and ICE Plots | Python Code | scikit-learn Package
12:57
Partial Dependence (PDPs) and Individual Conditional Expectation (ICE) Plots | Intuition and Math
A Data Odyssey
Partial Dependence (PDPs) and Individual Conditional Expectation (ICE) Plots | Intuition and Math
11:55
Permutation Feature Importance from Scratch | Explanation & Python Code
A Data Odyssey
Permutation Feature Importance from Scratch | Explanation & Python Code
13:10
Model Agnostic Methods for XAI | Global v.s. Local | Permutation v.s. Surrogate Models
A Data Odyssey
Model Agnostic Methods for XAI | Global v.s. Local | Permutation v.s. Surrogate Models
8:38
8 Plots for Explaining Linear Regression | Residuals, Weight, Effect & SHAP
A Data Odyssey
8 Plots for Explaining Linear Regression | Residuals, Weight, Effect & SHAP
13:39
Feature Selection using Hierarchical Clustering | Python Tutorial
A Data Odyssey
Feature Selection using Hierarchical Clustering | Python Tutorial
15:55
8 Characteristics of a Good Machine Learning Feature | Predictive, Variety, Interpretability, Ethics
A Data Odyssey
8 Characteristics of a Good Machine Learning Feature | Predictive, Variety, Interpretability, Ethics
16:16
Interpretable Feature Engineering | How to Build Intuitive Machine Learning Features
A Data Odyssey
Interpretable Feature Engineering | How to Build Intuitive Machine Learning Features
15:07
Modelling Non-linear Relationships with Regression
A Data Odyssey
Modelling Non-linear Relationships with Regression
9:32
Explaining Machine Learning to a Non-technical Audience
A Data Odyssey
Explaining Machine Learning to a Non-technical Audience
13:23
Get more out of Explainable AI (XAI): 10 Tips
A Data Odyssey
Get more out of Explainable AI (XAI): 10 Tips
13:47
The 6 Benefits of Explainable AI (XAI) | Improve accuracy, decrease harm and tell better stories
A Data Odyssey
The 6 Benefits of Explainable AI (XAI) | Improve accuracy, decrease harm and tell better stories
15:05
Introduction to Explainable AI (XAI) | Interpretable models, agnostic methods, counterfactuals
A Data Odyssey
Introduction to Explainable AI (XAI) | Interpretable models, agnostic methods, counterfactuals
11:51
Data Science vs Science | Differences & Bridging the Gap
A Data Odyssey
Data Science vs Science | Differences & Bridging the Gap
11:09
About the Channel and my Background | ML, XAI and Remote Sensing
A Data Odyssey
About the Channel and my Background | ML, XAI and Remote Sensing
3:32
SHAP for Binary and Multiclass Target Variables | Code and Explanations for Classification Problems
A Data Odyssey
SHAP for Binary and Multiclass Target Variables | Code and Explanations for Classification Problems
12:59
Introduction to Algorithm Fairness | Causes, Measuring & Preventing Unfairness in Machine Learning
A Data Odyssey
Introduction to Algorithm Fairness | Causes, Measuring & Preventing Unfairness in Machine Learning
5:46
SHAP Violin and Heatmap Plots | Interpretations and New Insights
A Data Odyssey
SHAP Violin and Heatmap Plots | Interpretations and New Insights
5:26
Correcting Unfairness in Machine Learning | Pre-processing, In-processing, Post-processing
A Data Odyssey
Correcting Unfairness in Machine Learning | Pre-processing, In-processing, Post-processing
9:01
Definitions of Fairness in Machine Learning | Equal Opportunity, Equalized Odds & Disparate Impact
A Data Odyssey
Definitions of Fairness in Machine Learning | Equal Opportunity, Equalized Odds & Disparate Impact
10:32
Exploratory Fairness Analysis | Quantifying Unfairness in Data
A Data Odyssey
Exploratory Fairness Analysis | Quantifying Unfairness in Data
7:47
5 Reasons for Unfair Models | Proxy Variables, Unbalanced Samples & Negative Feedback Loops
A Data Odyssey
5 Reasons for Unfair Models | Proxy Variables, Unbalanced Samples & Negative Feedback Loops
10:09
Feature Engineering with Image Data | Aims, Techniques & Limitations
A Data Odyssey
Feature Engineering with Image Data | Aims, Techniques & Limitations
9:03
Image Augmentation for Deep Learning | Benefits, Techniques & Best Practices
A Data Odyssey
Image Augmentation for Deep Learning | Benefits, Techniques & Best Practices
9:36
Interpretable vs Explainable Machine Learning
A Data Odyssey
Interpretable vs Explainable Machine Learning
7:07
4 Significant Limitations of SHAP
A Data Odyssey
4 Significant Limitations of SHAP
6:35
Shapley Values for Machine Learning
A Data Odyssey
Shapley Values for Machine Learning
11:06
The mathematics behind Shapley Values
A Data Odyssey
The mathematics behind Shapley Values
11:48
SHAP with Python (Code and Explanations)
A Data Odyssey
SHAP with Python (Code and Explanations)
15:41
SHAP values for beginners | What they mean and their applications
A Data Odyssey
SHAP values for beginners | What they mean and their applications
7:07
5 ways to use a Seaborn Heatmap
A Data Odyssey
5 ways to use a Seaborn Heatmap
3:02
Data Exploration with PCA
A Data Odyssey
Data Exploration with PCA
5:11