Explainable-by-design Deep Learning

Angelov, Plamen (2021) Explainable-by-design Deep Learning. In: IEEE Pervasive Computing, 1900-01-01.

Full text not available from this repository.

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.

Item Type:
Contribution to Conference (Speech)
Journal or Publication Title:
IEEE Pervasive Computing
Subjects:
ID Code:
151908
Deposited By:
Deposited On:
26 Feb 2021 14:15
Refereed?:
No
Published?:
Published
Last Modified:
15 Jun 2021 15:05