Home > Research > Publications & Outputs > Explainable-by-design Deep Learning

Electronic data

  • PerDL2021__keynotetalk

    Accepted author manuscript, 75.9 KB, PDF document

View graph of relations

Explainable-by-design Deep Learning

Research output: Contribution to conference - Without ISBN/ISSN Speech

Published
Publication date03/2021
<mark>Original language</mark>English
EventIEEE Pervasive Computing -
Duration: 1/01/1900 → …

Conference

ConferenceIEEE Pervasive Computing
Period1/01/00 → …

Abstract

MACHINE and AI justifiably attract the attention and interest not only of the wider scientific community and industry, but also society and policy makers. However,
even the most powerful (in terms of accuracy) algorithms such as deep learning (DL) can give a wrong output, which may be fatal. Due to the opaque and cumbersome model structure used by DL, some authors started to talk about a dystopian “black box” society. Despite the success in this area, the way computers learn is still principally different from the way people acquire new knowledge, recognise
objects and make decisions.