What is Explainable AI?

The field aimed at making machine learning models understandable to humans

A model could reject your application for a mortgage or diagnose you with cancer. These decisions have consequences. Serious consequences. Even if they are correct, we would expect an explanation. To get these we look to the field of explainable AI. 

Read on Medium

 Latest YouTube

I have too many houseplants—and what better way to manage them than by building a machine learning model? But what if the model ends up being right for the wrong reasons? In this video, we: 🌱 Build a dataset of my four plants: Rudo, Baya, Greg, and Yuki. 📸 Train a convolutional neural network (CNN) to classify plant images. 🤔 Use Explainable AI (XAI) methods to uncover a critical flaw in the model. When evaluating the model on new data, I discovered it was using pot colors—not plants—to make predictions. This bias revealed how easily machine learning models can fail if datasets aren't diverse enough. This video is an introduction to my free Explainable AI for Computer Vision course, where you'll learn how XAI methods like Grad-CAM, SHAP, and occlusion mapping can uncover hidden biases, improve fairness, and build trust in your models. Learn why XAI is essential for developing better, more transparent machine learning models. Subscribe and join the journey! 🌟 🚀 Free Course 🚀 XAI for CV: adataodyssey.com/xai-for-cv Paid version (get now at a discounted price): https://adataodyssey.com/courses/xai-for-cv/ eBook: (COMING SOON) 🚀 Other XAI Courses 🚀 XAI with Python: https://adataodyssey.com/courses/xai-with-python/ SHAP with Python: https://adataodyssey.com/courses/shap-with-python/ 🚀 Companion article 🚀 https://adataodyssey.com/the-importance-of-explainable-ai-xai-in-computer-vision/ 🚀 Useful playlists 🚀 XAI for CV: https://www.youtube.com/playlist?list=PLqDyyww9y-1QA4-o4tTAF_iD5cKCC1qEA XAI: https://www.youtube.com/playlist?list=PLqDyyww9y-1SwNZ-6CmvfXDAOdLS7yUQ4 SHAP: https://www.youtube.com/playlist?list=PLqDyyww9y-1SJgMw92x90qPYpHgahDLIK Algorithm fairness: https://www.youtube.com/playlist?list=PLqDyyww9y-1Q0zWbng6vUOG1p3oReE2xS 🚀 Get in touch 🚀 Medium: https://conorosullyds.medium.com/ Bluesky: https://bsky.app/profile/conorosullyds.bsky.social Threads: https://www.threads.net/@conorosullyds Twitter: https://twitter.com/conorosullyDS Website: https://adataodyssey.com/ 🚀 Chapters 🚀 00:00 Introduction 0:33 Creating the Pot Plant Dataset 00:59 Model Training 02:49 Debugging the model with Grad-CAM
Debugging a Pot Plant Detector | FREE Python Course | L1 – The Importance of XAI in Computer Vision
🚀 Course 🚀 Free: https://adataodyssey.com/permutation-channel-importance Paid: https://adataodyssey.com/courses/xai-for-cv/ We dive into Permutation Channel Importance (PCI) and show you how to apply it using Python. We'll work with the Landsat Irish Coastal Segmentation (LICS) Dataset, a resource for advancing deep learning methods in coastal water body segmentation. This dataset includes 100 multispectral test images, each with a binary segmentation mask that classifies pixels as either land or ocean. This is a great start if you are interested in applying Explainable AI methods to remote sensing machine learning models. 🚀 Useful playlists 🚀 XAI for CV: https://youtube.com/playlist?list=PLqDyyww9y-1QA4-o4tTAF_iD5cKCC1qEA&si=oJSL6o40xNpJqqkT XAI: https://www.youtube.com/playlist?list=PLqDyyww9y-1SwNZ-6CmvfXDAOdLS7yUQ4 SHAP: https://www.youtube.com/playlist?list=PLqDyyww9y-1SJgMw92x90qPYpHgahDLIK Algorithm fairness: https://www.youtube.com/playlist?list=PLqDyyww9y-1Q0zWbng6vUOG1p3oReE2xS 🚀 Get in touch 🚀 Medium: https://conorosullyds.medium.com/ Threads: https://www.threads.net/@conorosullyds Twitter: https://twitter.com/conorosullyDS Website: https://adataodyssey.com/ 🚀 Chapters 🚀 00:00 Introduction 01:43 Landsat Irish Coastal Segmentation (LICS) dataset 02:54 Exploring LICS 09:58 Shuffling a channel 12:53 Applying PCI
Applying Permutation Channel Importance (PCI) to a Remote Sensing Model | Python Tutorial
🚀 Course 🚀 Free: https://adataodyssey.com/permutation-channel-importance Paid: https://adataodyssey.com/courses/xai-for-cv/ In this video, we dive into Permutation Channel Importance (PCI) — a powerful explainability technique that helps identify which color channels (like RGB in regular images) contribute to a machine leanring model's predictions. PCI is a simple yet effective approach within Explainable AI (XAI) and serves as a foundation for understanding more advanced computer vision methods, such as occlusion and SHAP, which also use permutations. 🚀 Useful playlists 🚀 XAI: https://www.youtube.com/playlist?list=PLqDyyww9y-1SwNZ-6CmvfXDAOdLS7yUQ4 SHAP: https://www.youtube.com/playlist?list=PLqDyyww9y-1SJgMw92x90qPYpHgahDLIK Algorithm fairness: https://www.youtube.com/playlist?list=PLqDyyww9y-1Q0zWbng6vUOG1p3oReE2xS 🚀 Get in touch 🚀 Medium: https://conorosullyds.medium.com/ Threads: https://www.threads.net/@conorosullyds Twitter: https://twitter.com/conorosullyDS Website: https://adataodyssey.com/ 🚀 Chapters 🚀 00:00 Introduction 01:59 Permutation in comuter vision 03:46 The PCI algorithm 06:14 Applications of PCI
Explaining Computer Vision Models with PCI
See more Subscribe