Accepted author manuscript, 75.9 KB, PDF document
Research output: Contribution to conference - Without ISBN/ISSN › Speech
Research output: Contribution to conference - Without ISBN/ISSN › Speech
}
TY - CONF
T1 - Explainable-by-design Deep Learning
AU - Angelov, Plamen
PY - 2021/3
Y1 - 2021/3
N2 - 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, recogniseobjects and make decisions.
AB - 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, recogniseobjects and make decisions.
KW - Explainable AI
M3 - Speech
T2 - IEEE Pervasive Computing
Y2 - 1 January 1900
ER -