A view to a KILL: Knowledge Injection via Lambda Layer


pagemagnifierBibTeX_logo.pngmagnifierpage_white_acrobatmagnifier

Matteo Magnini, Giovanni Ciatto, Andrea Omicini

Angelo Ferrando, Viviana Mascardi (eds.)
“WOA 2022 – 23rd Workshop “From Objects to Agents””, pages 61–76
CEUR Workshop Proceedings (AIxIA Series) 3261
Sun SITE Central Europe, RWTH Aachen University
November 2022

We propose KILL (Knowledge Injection via Lambda Layer) as a novel method for the injection of symbolic knowledge into neural networks (NN) allowing data scientists to control what the network should (not) learn. Unlike other similar approaches, our method does not (i) require ground input formulae, (ii) impose any constraint on the NN undergoing injection, (iii) affect the loss function of the NN. Instead, it acts directly at the backpropagation level, by increasing penalty whenever the NN output is violating the injected knowledge. Experiments are reported to demonstrate the potential (and limits) of our approach.

(keywords) symbolic knowledge injection; AI; ML; neural networks; KILL; PSyKI

Talks

Journals & Series

Events

  • 23rd Workshop “From Objects to Agents” (WOA 2022) — 01/09/2022–03/09/2022

Publication

— authors

— editors

Angelo Ferrando, Viviana Mascardi

— status

published

— sort

paper in proceedings

— publication date

November 2022

— volume

WOA 2022 – 23rd Workshop “From Objects to Agents”

— series

CEUR Workshop Proceedings / AIxIA Series

— volume

3261

— pages

61–76

— number of pages

16

URLs

original page  |  original PDF  |  open access PDF

identifiers

— DBLP

conf/woa/MagniniCO22

— IRIS

11585/899373

— Scholar

514437633827732665

— print ISSN

1613-0073

files

Open Access PDF

Partita IVA: 01131710376 — Copyright © 2008–2023 APICe@DISI – PRIVACY