Intentional Forgetting in Artificial Intelligence Systems: Perspectives and Challenges

@inproceedings{Timm2018IntentionalFI,
  title={Intentional Forgetting in Artificial Intelligence Systems: Perspectives and Challenges},
  author={Ingo J. Timm and Steffen Staab and Michael Siebers and Claudia Schon and Ute Schmid and Kai Sauerwald and Lukas Reuter and Marco Ragni and Claudia Nieder{\'e}e and Heiko Maus and Gabriele Kern-Isberner and Christian Jilek and Paulina Friemann and Thomas Eiter and Andreas R. Dengel and Hannah Dames and Tanja Bock and Jan Ole Berndt and Christoph Beierle},
  booktitle={KI},
  year={2018}
}
Current trends, like digital transformation and ubiquitous computing, yield in massive increase in available data and information. In artificial intelligence (AI) systems, capacity of knowledge bases is limited due to computational complexity of many inference algorithms. Consequently, continuously sampling information and unfiltered storing in knowledge bases does not seem to be a promising or even feasible strategy. In human evolution, learning and forgetting have evolved as advantageous… 

Intentional Forgetting: An Emerging Field in AI and Beyond

TLDR
In human evolution, learning has evolved as a key strategy for adaptation and humans integrate complex forms of interaction and information exchange in the learning process to include other people’s experiences in addition to stimulus-responseconditioning.

Managed Forgetting to Support Information Management and Knowledge Work

TLDR
The untapped potential of more explicated user context as well as features inspired by memory inhibition are addressed, which is the current focus of research.

Uncovering the Data-Related Limits of Human Reasoning Research: An Analysis based on Recommender Systems

TLDR
This work investigates potential data-related reasons for the problems in human reasoning research by comparing model performances on human and artificially generated datasets and introduces the tools and presents initial results to pioneer a new paradigm for investigating and modeling reasoning focusing on predicting responses for individual human reasoners.

A TRANSFORMAÇÃO DIGITAL SOB A ÓTICA DA ENGENHARIA DO CONHECIMENTO: UMA REVISÃO SOBRE O USO DE ONTOLOGIAS COMO MODELO

TLDR
The correct knowledge management within an organization adds strategic and decisive values so that it stands out in a competitive market, because from the construction of intelligent knowledge systems, there is optimization and flexibility for a quick adaptation that conveniently meets the needs imposed by the market.

References

SHOWING 1-10 OF 32 REFERENCES

A Knowledge Level Account of Forgetting

  • J. Delgrande
  • Philosophy, Computer Science
    J. Artif. Intell. Res.
  • 2017
TLDR
The central thesis is that forgetting amounts to a reduction in the language, specifically the signature, of a logic, which provides a uniform approach to forgetting, with a definition that is applicable to any logic with a well-defined consequence relation.

Forgetting for knowledge bases in DL-Lite

TLDR
This work presents the first solution to the problem of omitting concepts and roles from knowledge bases of description logics (DLs) by adapting the technique of forgetting, previously used in other domains.

Forgetful Digital Memory: Towards Brain-Inspired Long-Term Data and Information Management

TLDR
The goal is to introduce an alternative to the dominating keep-it-all strategy for digital content, which ensures that the important content is kept safe, useful, and understandable over time.

Requirements for a companion system to support identifying irrelevancy

TLDR
Though forgetting seems to be an everyday hassle, forgetting information not needed in the current context is helpful, even necessary, and goal-directed forgetting is recommended.

Ultra-Strong Machine Learning: comprehensibility of programs learned with ILP

TLDR
A definition of comprehensibility of hypotheses which can be estimated using human participant trials is provided and implies the existence of a class of relational concepts which are hard to acquire for humans, though easy to understand given an abstract explanation.

Companion Cognitive Systems: A Step towards Human-Level AI

TLDR
The ideas the team is using to develop the first architecture for Companions are analogical processing, grounded in cognitive science for reasoning and learning, sketching and concept maps to improve interactivity, and a distributed agent architecture hosted on a cluster to achieve performance and longevity.

The Forgotten Needle in My Collections: Task-Aware Ranking of Documents in Semantic Information Space

TLDR
This work presents a ranking method, which unifies activity logs and semantic information about documents into a common framework to identify important documents to the user's current tasks, and shows that this approach outperforms the baseline methods for both subsequent access prediction and the effectiveness in ranking important documents.

Foundations of distributed artificial intelligence

TLDR
This paper presents a meta-modelling architecture for distributed artificial intelligence that automates the very labor-intensive and therefore time-heavy and expensive process of designing and implementing distributed systems.

Emotional constraints on intentional forgetting

Skeptical Inference Based on C-Representations and Its Characterization as a Constraint Satisfaction Problem

TLDR
It is shown that c-inference preserves the properties of solving irrelevance and subclass inheritance which are met by every single c-representation, and is characterized as a constraint satisfaction problem so that constraint solvers can be used for its implementation.