Stack Overflow
Stack Overflow

Questions tagged [xai]

29 questions
3
votes
1 answer

SHAP: How do I interpret expected values for force_plot?

I'm trying to create a force_plot for my Random Forest model that has two classes (1 and 2), but I am a bit confused about the parameters for the force_plot. I have two different force_plot parameters I can provide the…
Penguines
  • 53
  • 3
2
votes
1 answer

What does the derivative of class score respect to feature map represent for?

I'm learning about XAI and I have a question about the derivative of the network. Assume I have a CNN model which gives 4 output representing 4 classes, and I have one target layer (L) from which I want to extract information when I pass the image…
KhanhNguyen
  • 41
  • 2
2
votes
0 answers

How to use GradCAM for multichannel 1D CNN models

I have some multi-channel time series data which I want to use as input to a 1D Convolutional Neural Network classifier. Furthermore, I want to test the model and provide an activation map for these test data. I have already implemented a solution…
bjornsing
  • 322
  • 6
  • 25
1
vote
0 answers

using SHAP with Inception V3

I am trying to run GradientExplainer method of SHAP on a trained Inception V3 model. I could do it without a problem on a VGG16 and MobileNet. The difference between Inception and those two models is the input dimension shape being 299 instead of…
Maral
  • 65
  • 8
1
vote
0 answers

How do you specify multiple values for the inputTensorName key in INPUTMETADATA spec in Vertex Explainable AI for a Functional API model?

I want to add explanation to my model running in Vertex AI using the Vertex AI SDK.I get a silent error when running the batch prediction using ModelBatchPredictOp, where the ModelBatchPredictOp node runs infinitely.Here is my ModelBatchPredictOp…
Kev_in
  • 11
  • 3
1
vote
1 answer

SHAP xAI Graph scattered points

I use the SHAP xAI in Python for explaining the whole test data as can be seen . I would like to know how are the points scattered in each line? What are the denser point areas meaning? Why are there spaces between the scattered areas in each row?
Avi
  • 2,247
  • 4
  • 30
  • 52
1
vote
1 answer

SHAP values interpretation for multi-class

I'm looking at the Iris Dataset where I have calculated SHAP_values for my X_test dataset, I have provided the first five of each array as example: [ array([[-0.02994951, -0.00631915, -0.11904487, -0.13368648], …
Plewis
  • 119
  • 10
1
vote
0 answers

unsupported operand type(s) for -: 'str' and 'str' - Implementation LimeTabularExplainer

my issue is that I get the following error enter image description here when I try to follow the implementation given in the…
Manu675
  • 11
  • 3
1
vote
1 answer

How to improve model's performance base on XAI methods

I'm learning about explainable AI (XAI) and some of papers I've read say that we can use XAI to improve model's performance. It seems quite a new problem cuz I think when the model has already converged, it's impossible to find a new global minimum…
KhanhNguyen
  • 41
  • 2
0
votes
0 answers

CF-GNNExplainer: No perturbation on 3rd GCN-layer in the given model architecture

My question refers to the official implementation of CF-GNNExplainer on Github: https://github.com/a-lucic/cf-gnnexplainer When the perturbed model is built, the first 2 ConvLayers are the newly created perturbed layers while the 3rd layer is a…
Patrick
  • 1
0
votes
0 answers

Feature Importance for FT Transformer

I hope someone is able to shed light on this. I was reading through the codes on this link with regards to getting feature importance from attention…
DDM
  • 303
  • 4
  • 19
0
votes
0 answers

How to use SHAP for VGG16 for image classification through Transfer Learning

I have good understanding of applying Transfer learning for image classification. However I wanted to apply the SHAP (SHapley Additive exPlanation) for TL based image classification. I found that SHAP works for image classification without Transfer…
Nhqazi
  • 732
  • 3
  • 12
  • 30
0
votes
0 answers

How to select the target layers for explainability in deep learning?

I am investigating different explainability methods along with different models. I am using the library "pytorch_grad_cam" but I am still unable to know how to select the target layers so that I can get the best possible results of explainability.…
Nussair Hroub
  • 1
  • 3
0
votes
0 answers

IndexError: index 15 is out of bounds for axis 1 with size 15

Hello I am trying to incorporate LIME and GradCAM for my code that trains a deep learning model using Keras. A lot of this code if old and taken from a github repository for some research I am doing. Due to this, many of the libraries are outdated.…
Rayaan
  • 1
0
votes
0 answers

LIME does not show the features' scores for positive class explanation

i'm trying to explain the prediction for binary text classification model (LSTM&GRU using BERT embedding) with LIME, it highlights the features for both classes, but it shows the score for each feature just for class 0. even if i tried different…
Rarai
  • 1
1
2