Random Forest Model and Sample Explainer for Non-experts in Machine Learning – Two Case Studies

Petković, Dragutin; Alavi, Amir; Cai, Derun; Wong, Mike

doi:10.1007/978-3-030-68796-0_5

Cited by 5 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is why they are called "sample-based" methods. 13 In the following, we will briefly explain the "black box" methods and focus on "white box" methods in image classification tasks.…”

Section: Topology Of Explanation Methods For Image Classification Tasksmentioning

confidence: 99%

See 1 more Smart Citation

Review of white box methods for explanations of convolutional neural networks in image classification tasks

2021

View full text Add to dashboard Cite

In recent years, deep learning has become prevalent to solve applications from multiple domains. Convolutional neural networks (CNNs) particularly have demonstrated state-ofthe-art performance for the task of image classification. However, the decisions made by these networks are not transparent and cannot be directly interpreted by a human. Several approaches have been proposed to explain the reasoning behind a prediction made by a network. We propose a topology of grouping these methods based on their assumptions and implementations. We focus primarily on white box methods that leverage the information of the internal architecture of a network to explain its decision. Given the task of image classification and a trained CNN, our work aims to provide a comprehensive and detailed overview of a set of methods that can be used to create explanation maps for a particular image, which assign an importance score to each pixel of the image based on its contribution to the decision of the network. We also propose a further classification of the white box methods based on their implementations to enable better comparisons and help researchers find methods best suited for different scenarios.

show abstract

“…This is why they are called "sample-based" methods. 13 In the following, we will briefly explain the "black box" methods and focus on "white box" methods in image classification tasks.…”

Section: Topology Of Explanation Methods For Image Classification Tasksmentioning

confidence: 99%

“…To improve the stability of the LRP-0 rule, a small positive term ε is added to the denominator as shown in Eq. (13). The ε term also reduces the flow of the relevance if the activation of the neuron is very small or there is a weak connection between the two neurons.…”

Section: Layer-wise Relevance Propagationmentioning

confidence: 99%

Review of white box methods for explanations of convolutional neural networks in image classification tasks

2021

View full text Add to dashboard Cite

show abstract

“…This is why they are called "sample-based" methods. 11 In the following, we will briefly explain the "Black box" methods and focus on "White box" methods in image classification tasks.…”

Section: Topology Of Explanation Methods For Image Classification Tasksmentioning

confidence: 99%

White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks

Ayyar,

Benois-Pineau,

Zemmari

2021

Preprint

View full text Add to dashboard Cite

In recent years, deep learning has become prevalent to solve applications from multiple domains. Convolutional Neural Networks (CNNs) particularly have demonstrated state of the art performance for the task of image classification. However, the decisions made by these networks are not transparent and cannot be directly interpreted by a human. Several approaches have been proposed to explain to understand the reasoning behind a prediction made by a network. In this paper, we propose a topology of grouping these methods based on their assumptions and implementations. We focus primarily on white box methods that leverage the information of the internal architecture of a network to explain its decision. Given the task of image classification and a trained CNN, this work aims to provide a comprehensive and detailed overview of a set of methods that can be used to create explanation maps for a particular image, that assign an importance score to each pixel of the image based on its contribution to the decision of the network. We also propose a further classification of the white box methods based on their implementations to enable better comparisons and help researchers find methods best suited for different scenarios.

show abstract

“…The delta between the original and the tweaked value represents the "tweaking cost" required to move the instance into the target class. Random forest model and sample explainer (RFEX) [62] returns numerical explanations, formatted as tables, of the predictions made by random forests in binary classification problems. The table contains the features of the dataset ranked according to their predictive power, measured by their mean decrease in accuracy, cumulative F 1 score and Cohen distance.…”

Section: Ensemblesmentioning

confidence: 99%

Classification of Explainable Artificial Intelligence Methods through Their Output Formats

Vilone

Longo

2021

MAKE

103

View full text Add to dashboard Cite

Machine and deep learning have proven their utility to generate data-driven models with high accuracy and precision. However, their non-linear, complex structures are often difficult to interpret. Consequently, many scholars have developed a plethora of methods to explain their functioning and the logic of their inferences. This systematic review aimed to organise these methods into a hierarchical classification system that builds upon and extends existing taxonomies by adding a significant dimension—the output formats. The reviewed scientific papers were retrieved by conducting an initial search on Google Scholar with the keywords “explainable artificial intelligence”; “explainable machine learning”; and “interpretable machine learning”. A subsequent iterative search was carried out by checking the bibliography of these articles. The addition of the dimension of the explanation format makes the proposed classification system a practical tool for scholars, supporting them to select the most suitable type of explanation format for the problem at hand. Given the wide variety of challenges faced by researchers, the existing XAI methods provide several solutions to meet the requirements that differ considerably between the users, problems and application fields of artificial intelligence (AI). The task of identifying the most appropriate explanation can be daunting, thus the need for a classification system that helps with the selection of methods. This work concludes by critically identifying the limitations of the formats of explanations and by providing recommendations and possible future research directions on how to build a more generally applicable XAI method. Future work should be flexible enough to meet the many requirements posed by the widespread use of AI in several fields, and the new regulations.

show abstract

Random Forest Model and Sample Explainer for Non-experts in Machine Learning – Two Case Studies

Cited by 5 publications

References 10 publications

Review of white box methods for explanations of convolutional neural networks in image classification tasks

Review of white box methods for explanations of convolutional neural networks in image classification tasks

White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks

Classification of Explainable Artificial Intelligence Methods through Their Output Formats

Contact Info

Product

Resources

About