A Survey on the Explainability of Supervised Machine Learning
Authors: Nadia Burkart, Marco F. Huber
JAIR 2021 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We will conclude each chapter that describes a category according to the definitions in section 3.1 with an illustrative example on the well-known IRIS data set for the task of classification (Dua & Graff, 2017). The instance we use for the local procedures is taken from the class virginica with the feature values [5.8, 2.8, 5.1, 2.4]. |
| Researcher Affiliation | Academia | Nadia Burkart EMAIL Fraunhofer Center of Machine Learning, Fraunhofer Institute for Optronics, System Technologies, and Image Exploitation IOSB, Interactive Analysis and Diagnosis Fraunhoferstrasse 1, 76131 Karlsruhe, Germany; Marco F. Huber EMAIL University of Stuttgart, Institute of Industrial Manufacturing and Management IFF, Fraunhofer Institute for Manufacturing Engineering and Automation IPA, Center for Cyber Cognitive Intelligence (CCI), Nobelstrasse 12, 70569 Stuttgart, Germany |
| Pseudocode | No | The paper describes various algorithms and methods but does not present them in structured pseudocode or algorithm blocks. It uses descriptive text and mathematical formulations. |
| Open Source Code | No | The paper does not provide any statement about the availability of its own source code, nor does it include links to a code repository for the methodology described in this survey. |
| Open Datasets | Yes | We will conclude each chapter that describes a category according to the definitions in section 3.1 with an illustrative example on the well-known IRIS data set for the task of classification (Dua & Graff, 2017). |
| Dataset Splits | No | The paper mentions the use of the IRIS dataset for illustrative examples, stating 'The instance we use for the local procedures is taken from the class virginica with the feature values [5.8, 2.8, 5.1, 2.4].' However, it does not specify any training, validation, or test dataset splits or percentages required for reproducing experiments. |
| Hardware Specification | No | This paper is a survey and does not present original experimental results that would require a description of hardware specifications. The 'use cases' are illustrative and do not include details about specific GPUs, CPUs, or other computational resources used. |
| Software Dependencies | No | The paper references various machine learning algorithms and tools (e.g., 'PyTorch', 'Caffe', 'treeinterpreter') but does not specify any particular software dependencies with version numbers for the analysis or illustrative examples presented by the authors. |
| Experiment Setup | Yes | Figure 4 illustrates a decision tree with the depth of two. ... Figure 5 illustrates a decision tree with the depth of three. |