Learn about popular Explainable AI algorithms such as integrated gradient, LIME, class activation maps, counterfactual explanations, etc.

docker.tar.gz

Explainable AI is a set of tools and frameworks that helps you understand and interpret the internal logic behind the predictions made by a deep learning network. With this, you can generate insights into the behavior and working of the model to mitigate issues around it in the development phase.

In this course, you will be introduced to popular Explainable AI algorithms such as smooth gradient, integrated gradient, LIME, class activation maps, counterfactual explanations, feature attributions, etc., for image classification networks such as MobileNet-V2 trained on large-scale datasets like ImageNet-1K.

By the end of this course, you will understand the need for Explainable AI and be able to design and implement popular explanation algorithms like saliency maps, class activation maps, counterfactual explanations, etc. You will be able to evaluate and quantify the quality of the neural network explanations via several interpretability metrics.

Master Explainable AI: Interpreting Image Classifier Decisions

make the training of deep neural networks faster

improve the generalization of deep neural networks

interpret and explain the decisions made by deep neural networks

make the predictions of deep neural networks robust to data distribution

**(Fill in the blank.)** The role of Explainable AI is to ________.

(Fill in the blank.) The role of Explainable AI is to ________.

They use gradient information from the penultimate convolutional layers to assign importance scores.

They're images that look similar to the original image but result in an altered prediction.

They're explanations produced by assigning image regions or pixels an importance score based on how their removal affects the model prediction.

They're explanations that produce prototype images similar to the original image representing a particular class.

Which statement is *true* about counterfactual explanations?

Which statement is true about counterfactual explanations?

$\left ( 2x_1x_2^2 - \cos(x_1), \ 2x_2x_1^2 + \frac{1}{x_2} \right )$

$\left ( 2x_1x_2^2 + \cos(x_1), \ 2x_2x_1^2 - \frac{1}{x_2} \right )$

$\left ( 2x_1x_2^2 + \cos(x_1), \ 2x_2x_1^2 + \frac{1}{x_2} \right )$

$\left ( 2x_1x_2 + \cos(x_1), \ 2x_2x_1^2 + \frac{1}{x_2} \right )$

**(Fill in the blank.)** The gradient of the function $f((x_1,x_2)) =x_1^2x_2^2+ \sin(x_1)+\log(x_2)$ with respect to $(x_1,x_2)$ is ________.

(Fill in the blank.) The gradient of the function <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>f</mi><mo stretchy="false">(</mo><mo stretchy="false">(</mo><msub><mi>x</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>x</mi><mn>2</mn></msub><mo stretchy="false">)</mo><mo stretchy="false">)</mo><mo>=</mo><msubsup><mi>x</mi><mn>1</mn><mn>2</mn></msubsup><msubsup><mi>x</mi><mn>2</mn><mn>2</mn></msubsup><mo>+</mo><mi>sin</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>x</mi><mn>1</mn></msub><mo stretchy="false">)</mo><mo>+</mo><mi>log</mi><mo>⁡</mo><mo stretchy="false">(</mo><msub><mi>x</mi><mn>2</mn></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">f((x_1,x_2)) =x_1^2x_2^2+ \sin(x_1)+\log(x_2)</annotation></semantics></math>f((x1​,x2​))=x12​x22​+sin(x1​)+log(x2​) with respect to <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><msub><mi>x</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>x</mi><mn>2</mn></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(x_1,x_2)</annotation></semantics></math>(x1​,x2​) is ________.

**(Fill in the blank.)** The gradient of the function $f((x_1,x_2)=\exp(x_1^2)+\log(x_2^2)$ with respect to $(x_1,x_2)$ at $(1,2)$ is ________.

(Fill in the blank.) The gradient of the function <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mi>f</mi><mo stretchy="false">(</mo><mo stretchy="false">(</mo><msub><mi>x</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>x</mi><mn>2</mn></msub><mo stretchy="false">)</mo><mo>=</mo><mi>exp</mi><mo>⁡</mo><mo stretchy="false">(</mo><msubsup><mi>x</mi><mn>1</mn><mn>2</mn></msubsup><mo stretchy="false">)</mo><mo>+</mo><mi>log</mi><mo>⁡</mo><mo stretchy="false">(</mo><msubsup><mi>x</mi><mn>2</mn><mn>2</mn></msubsup><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">f((x_1,x_2)=\exp(x_1^2)+\log(x_2^2)</annotation></semantics></math>f((x1​,x2​)=exp(x12​)+log(x22​) with respect to <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><msub><mi>x</mi><mn>1</mn></msub><mo separator="true">,</mo><msub><mi>x</mi><mn>2</mn></msub><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(x_1,x_2)</annotation></semantics></math>(x1​,x2​) at <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><mo stretchy="false">(</mo><mn>1</mn><mo separator="true">,</mo><mn>2</mn><mo stretchy="false">)</mo></mrow><annotation encoding="application/x-tex">(1,2)</annotation></semantics></math>(1,2) is ________.

Which statement is *true* about perturbation-based explanations?

Which statement is true about perturbation-based explanations?

Evaluate yourself on the concepts learned in this chapter.

Introduction to Explainable AI

Saliency Maps

Class Activation Maps

Miscellaneous Methods

Metrics of Interpretability

Final Assessment

Weakly Supervised Object Localization

Introductory Quiz on Explainable AI