Making a Neural Network Learn to Say Don't Know.

Date of Submission

December 2020

Date of Award

Winter 12-12-2021

Institute Name (Publisher)

Indian Statistical Institute

Document Type

Master's Dissertation

Degree Name

Master of Technology

Subject Name

Computer Science

Department

Electronics and Communication Sciences Unit (ECSU-Kolkata)

Supervisor

Pal, Nikhil Ranjan (ECSU-Kolkata; ISI)

Abstract (Summary of the Work)

Classification problem is a popular topic within machine learning community. One of the major problem in classification task is how to handle incoming patterns which are unusual and different in some measure. For such novel input the classifier should be able to distinguish them as unknown type and don't make any decision. In this work we try to address that problem.

Comments

ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28842711

Control Number

ISI-DISS-2020-23

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

DOI

http://dspace.isical.ac.in:8080/jspui/handle/10263/7162

This document is currently not available here.

Share

COinS