Explainable AI: Scene Classification and GradCam Visualization

4.7
stars
38 ratings
Offered By
Coursera Project Network
1,864 already enrolled
In this Guided Project, you will:

Understand the theory and intuition behind Deep Neural Networks, Residual Nets, and Convolutional Neural Networks (CNNs)

Build a deep learning model based on Convolutional Neural Network and Residual blocks using Keras with Tensorflow 2.0 as a backend

Visualize the Activation Maps used by CNN to make predictions using Grad-CAM and Deploy the trained model using Tensorflow Serving

Clock2 hours
IntermediateIntermediate
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this 2 hour long hands-on project, we will train a deep learning model to predict the type of scenery in images. In addition, we are going to use a technique known as Grad-Cam to help explain how AI models think. This project could be practically used for detecting the type of scenery from the satellite images.

Skills you will develop

Deep LearningMachine LearningPython ProgrammingArtificial Intelligence(AI)Computer Vision

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Understand the theory and intuition behind Deep Neural Networks, Residual Nets, and Convolutional Neural Networks (CNNs)

  2. Apply Python libraries to import, pre-process and visualize images

  3. Perform data augmentation to improve model generalization capability

  4. Build a deep learning model based on Convolutional Neural Network and Residual blocks using Keras with Tensorflow 2.0 as a backend

  5. Compile and fit Deep Learning model to training data

  6. Assess the performance of trained CNN and ensure its generalization using various KPIs such as accuracy, precision and recall

  7. Understand the theory and intuition behind GradCam and Explainable AI

  8. Visualize the Activation Maps used by CNN to make predictions using Grad-CAM

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Reviews

TOP REVIEWS FROM EXPLAINABLE AI: SCENE CLASSIFICATION AND GRADCAM VISUALIZATION

View all reviews

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.