Comparative study of xai using formal concept lattice and lime (Record no. 19044)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | a |
| 003 - CONTROL NUMBER IDENTIFIER | |
| control field | OSt |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20230327095303.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 230327b xxu||||| |||| 00| 0 eng d |
| 040 ## - CATALOGING SOURCE | |
| Original cataloging agency | AIKTC-KRRC |
| Transcribing agency | AIKTC-KRRC |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| 9 (RLIN) | 20276 |
| Author | Venkatsubramaniam, Bhaskaran |
| 245 ## - TITLE STATEMENT | |
| Title | Comparative study of xai using formal concept lattice and lime |
| 250 ## - EDITION STATEMENT | |
| Volume, Issue number | Vol.13(1), Oct |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Place of publication, distribution, etc. | Chennai |
| Name of publisher, distributor, etc. | ICT Academy |
| Year | 2022 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Pagination | 2782-2791p. |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | Local Interpretable Model Agnostic Explanation (LIME) is a<br/>technique to explain a black box machine learning model using a<br/>surrogate model approach. While this technique is very popular,<br/>inherent to its approach, explanations are generated from the surrogate<br/>model and not directly from the black box model. In sensitive domains<br/>like healthcare, this need not be acceptable as trustworthy. These<br/>techniques also assume that features are independent and provide<br/>feature weights of the surrogate linear model as feature importance. In<br/>real life datasets, features may be dependent and a combination of a set<br/>of features with their specific values can be the deciding factor rather<br/>than individual feature importance. They also generate random<br/>instances around the point of interest to fit the surrogate model. These<br/>random instances need not be part of the original source or may even<br/>turn out to be meaningless. In this work, we compare LIME to<br/>explanations from the formal concept lattice. This does not use a<br/>surrogate model but a deterministic approach by generating synthetic<br/>data that respects implications in the original dataset and not randomly<br/>generating it. It obtains crucial feature combinations with their values<br/>as decision factors without presuming dependence or independence of<br/>features. Its explanations not only cover the point of interest but also<br/>global explanation of the model, similar and contrastive examples<br/>around the point of interest. The explanations are textual and hence<br/>easier to comprehend than comprehending weights of a surrogate<br/>linear model to understand the black box model. |
| 650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| 9 (RLIN) | 4622 |
| Topical term or geographic name entry element | Computer Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| 9 (RLIN) | 20277 |
| Co-Author | Baruah, Pallav Kumar |
| 773 0# - HOST ITEM ENTRY | |
| Place, publisher, and date of publication | Chennai ICT Academy |
| Title | ICTACT Journal on Soft Computing (IJSC) |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| URL | https://ictactjournals.in/paper/IJSC_Vol_13_Iss_1_Paper_6_2782_2791.pdf |
| Link text | Click here |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | Dewey Decimal Classification |
| Koha item type | Articles Abstract Database |
| Withdrawn status | Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Home library | Current library | Shelving location | Date acquired | Total Checkouts | Barcode | Date last seen | Price effective from | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Dewey Decimal Classification | School of Engineering & Technology | School of Engineering & Technology | Archieval Section | 27/03/2023 | 2023-0515 | 27/03/2023 | 27/03/2023 | Articles Abstract Database |