=Paper= {{Paper |id=Vol-2786/Paper12 |storemode=property |title=Workshop on Novelties in Open World - Abstract |pdfUrl=https://ceur-ws.org/Vol-2786/Paper12.pdf |volume=Vol-2786 |authors=Bharat Bhargava |dblpUrl=https://dblp.org/rec/conf/isic2/Bhargava21a }} ==Workshop on Novelties in Open World - Abstract== https://ceur-ws.org/Vol-2786/Paper12.pdf
                                                                                                                                                                          78




Workshop on Novelties in Open World
Bharat Bhargavaa , Terrance E. Boultb , Larry Holderc and Eric J. Kildebeckd
a Purdue University, West Lafayette, Indiana, USA
b University of Colorado at Colorado Springs, United States
c Washington State University, Washington
d University of Texas at Dallas, United States



                                          Abstract
                                          Novelties are surprises that a system encounters. System must learn about the characteristics and detect, understand, and
                                          adapt to novelty in not only the environment but in agents that interact with it. The context, timing, duration, extent, duration
                                          of novelty must be considered in agent’s adaptation and accommodation. There is a need to build AI/ML systems that can
                                          adapt to fluid novelties in the open world.
                                              This workshop will contribute to scientific principles to quantify and characterize novelty in open-world domains. It will
                                          attempt to develop measures and evaluation criteria for behaviour of AI systems. The workshop will feature 3-4 speakers but
                                          we invite the participants to think and make contributions towards this problem during the workshop.


1. Motivation and Plans                                                                                                  How can a system continue to operate in un-
                                                                                                                         known adverse conditions and situations such
Novelties are found in many environments and agents                                                                      as collaborative attacks in cyberspace?
must learn about them and accommodate them. We
list a few examples to provide understanding and a ba-                                                                 • A fifth example of novelty is a man walking with
sis for discussion during the workshop.                                                                                  a cat (dog will not be novelty) or rhinoceros (ele-
   Examples of Novelties :                                                                                               phant or horse is not a novelty).

               • A car going on a steep hill in dark, rain. The car                                                    • A sixth example of novelty is big animals roam-
                 is not on the main road. Main road on flat ter-                                                         ing an urban area such as the street of San Fran-
                 rain, good weather will be normal. Steep hill,                                                          cisco or Manhattan (NY City) freely on roads
                 darkness, rain/snow and road with weak soil,                                                            and highways.
                 vegetation will be novelties.
                                                                                                                       • A seventh example will be a very expensive car
               • Second example is a person from the USA driv-                                                           parked in front of a house in a poor neighbour-
                 ing in India. Many novelties occur: no stop and                                                         hood or a really damaged/old car being driven
                 yield signs, left hand drive, mix of traffic vehicles                                                   by a billionaire.
                 (bicycle, rickshaw, horse/bullock/oxen driven
                 carts, scooters, three wheeler, along with trucks,                                                   Participants need to think of levels and categories
                 buses) and narrow single lane roads and unpaved                                                   of novelties. What are various ways the novelties can
                 roads. How can the driver (or drivers) visiting                                                   be formalized so as to represent them in a language
                 from the USA train, learn, and adjust to drive                                                    that can be understood by an AI system and a good
                 safely in India.                                                                                  user-interface can be created. Research is needed to
                                                                                                                   identify novelties that can be ignored (they have no
               • A third example is cheating or sudden change in                                                   impact on achieving the objectives of a system), can
                 the rules of playing games such as chess, basket-                                                 be tolerated with little damage or need immediate re-
                 ball, monopoly while the game is being played.                                                    sponse. We need to think of algorithms for AI sys-
                                                                                                                   tems to accommodate novelties and mediate between
               • A fourth example is attacks, malicious activities
                                                                                                                   agent’s actions and unknown/unexpected novelties so
                 and threats cyber or otherwise. How can a child
                                                                                                                   that the task for actions is successful. We need active
                 or older person deal with novelties of pickpock-
                                                                                                                   participation from researchers working in AI/ML and
                 ets, scoundrels, thieves, purse snatchers, etc.
                                                                                                                   semantic computing to make the workshop successful.
International Semantic Intelligence Conference (ISIC 2021), Feb 25-27,
2021, New Delhi, India
email: bbshail@purdue.edu (B. Bhargava)
orcid:
                                    © 2020 Copyright for this paper by its authors. Use permitted under Creative
                                    Commons License Attribution 4.0 International (CC BY 4.0).
 CEUR
 Workshop
 Proceedings
               http://ceur-ws.org
               ISSN 1613-0073       CEUR Workshop Proceedings (CEUR-WS.org)