Reader small image

You're reading from  The Deep Learning Architect's Handbook

Product typeBook
Published inDec 2023
PublisherPackt
ISBN-139781803243795
Edition1st Edition
Right arrow
Author (1)
Ee Kin Chin
Ee Kin Chin
author image
Ee Kin Chin

Ee Kin Chin is a Senior Deep Learning Engineer at DataRobot. He holds a Bachelor of Engineering (Honours) in Electronics with a major in Telecommunications. Ee Kin is an expert in the field of Deep Learning, Data Science, Machine Learning, Artificial Intelligence, Supervised Learning, Unsupervised Learning, Python, Keras, Pytorch, and related technologies. He has a proven track record of delivering successful projects in these areas and is dedicated to staying up to date with the latest advancements in the field.
Read more about Ee Kin Chin

Right arrow

Exploring gradient-based prediction explanations

Most up-to-date neural network-based explanation techniques today are variations of using the gradients that can be obtained through backpropagation. Gradient-based explanations for neural network models work because they rely on the fundamental principle of how the weights in a neural network are updated during the training process using backpropagation. During backpropagation, the partial derivatives of the loss function concerning the weights in the network are calculated, which gives us the gradient of the loss function concerning the weights.

This gradient provides us with a measure of how much the input data contributes to the overall loss. Remember that gradients measure the sensitivity of the input value concerning the loss function. This means it provides the degree of fluctuation of the predictions when you modify the specific input value, which represents the importance of the input data. Input data can be chosen to be...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
The Deep Learning Architect's Handbook
Published in: Dec 2023Publisher: PacktISBN-13: 9781803243795

Author (1)

author image
Ee Kin Chin

Ee Kin Chin is a Senior Deep Learning Engineer at DataRobot. He holds a Bachelor of Engineering (Honours) in Electronics with a major in Telecommunications. Ee Kin is an expert in the field of Deep Learning, Data Science, Machine Learning, Artificial Intelligence, Supervised Learning, Unsupervised Learning, Python, Keras, Pytorch, and related technologies. He has a proven track record of delivering successful projects in these areas and is dedicated to staying up to date with the latest advancements in the field.
Read more about Ee Kin Chin