Content deleted Content added
←Created page with '{{User sandbox}} <!-- EDIT BELOW THIS LINE --> '''Explainable AI (XAI)''' is a neologism that has recently reached the parlance of Artificial Intelligence....' |
No edit summary |
||
Line 2:
<!-- EDIT BELOW THIS LINE -->
'''Explainable AI (''XAI'')''' is a neologism that has recently reached the parlance of [[Artificial Intelligence]]. It's purpose is to provide accountability when addressing technological innovations ascribed to dynamic and none linearly programmed systems e.g. [[Artificial neural networks]], [[Deep learning]], [[Genetic Algorithms]], etc.
As a term, it was introduced in 2016 by the DARPA organisation <ref>{{cite web|title=Explainable Artificial Intelligence (XAI)|url=https://www.darpa.mil/program/explainable-artificial-intelligence|website=DARPA|publisher=DARPA|accessdate=17 July 2017}}</ref>▼
It is asking the question of '''how''' algorithms arrive at the decisions they do. AI related algorithmic (supervised and unsupervised) practices work on a model of success that orientates towards some form of correct state with singular focus placed on an expected output e.g. an image recognition algorithm's level of success will be based on the algorithms ability to recognize certain objects, failure to do so will indicate that the algorithm requires further tuning. As the tuning level is dynamic, closely correlated to function refinement and training data-set, granular understanding of the underlying operational vectors is rarely introspected.
XAI aims to address this black-box approach and allow introspection of these dynamic systems tractable.
== Definition ==
The Darpa initiative defines XAI as the following:
"The Explainable AI (XAI) program aims to create a suite of machine learning techniques that:
* Produce more explainable models, while maintaining a high level of learning performance (prediction accuracy); and
▲
Fileless malware is sometimes considered synonymous with ''in-memory'' malware as both perform their core functionalities without writing data to disk during the lifetime of their operation. This has led some commentators to claim that this variant strain is nothing new and simply a “redefinition of the well-known term, memory resident virus”,<ref>{{cite web|title=Advanced volatile threat: New name for old malware technique?|url=http://www.csoonline.com/article/2132995/malware-cybercrime/advanced-volatile-threat--new-name-for-old-malware-technique-.html|website=CSO|publisher=CSO|accessdate=20 February 2017}}</ref> whose pedigree can be traced back to the 1980’s with the birth of the [[Timeline of computer viruses and worms|Lehigh Virus]] that was developed by the terms founder [[Fred Cohen]] and became influential with his paper on the topic.<ref>{{cite web|title=Computer Viruses - Theory and Experiments|url=http://web.eecs.umich.edu/~aprakash/eecs588/handouts/cohen-viruses.html|website=University of Michigan|accessdate=20 February 2017}}</ref>
Line 65 ⟶ 71:
{{DEFAULTSORT:Fileless malware}}
[[Category:
[[Category:Malware]]
| |||