Mesarovician Abstract Learning Systems

@inproceedings{Cody2021MesarovicianAL,
  title={Mesarovician Abstract Learning Systems},
  author={Tyler Cody},
  booktitle={AGI},
  year={2021}
}
  • Tyler Cody
  • Published in AGI 29 November 2021
  • Computer Science
The solution methods used to realize artificial general intelligence (AGI) may not contain the formalism needed to adequately model and characterize AGI. In particular, current approaches to learning hold notions of problem domain and problem task as fundamental precepts, but it is hardly apparent that an AGI encountered in the wild will be discernable into a set of domain-task pairings. Nor is it apparent that the outcomes of AGI in a system can be well expressed in terms of domain and task… 

Homomorphisms Between Transfer, Multi-Task, and Meta-Learning Systems

This manuscript formalizes transfer learning, multi-task learning, and meta-learning as abstract learning systems, consistent with the formal-minimalist abstract systems theory of Mesarovic and Takahara, and uses the presented formalism to relate the three concepts of learning in terms of composition, hierarchy, and structural homomorphism.

Core and Periphery as Closed-System Precepts for Engineering General Intelligence

This paper posits that engineering general intelligence requires new general systems precepts, termed the core and periphery, and explores their theoretical uses and substantiates discourse on a new framework for engineering.

Combinatorial coverage framework for machine learning in multi-domain operations

It is concluded that combinatorial coverage should be considered a core capability for supporting ML in MDO, and how coverage is oriented towards identifying gaps in and between sets of data is discussed.

References

SHOWING 1-10 OF 14 REFERENCES

Why Artificial Intelligence Needs a Task Theory - And What It Might Look Like

A task theory would enable addressing tasks at the class level, bypassing their specifics, providing the appropriate formalization and classification of tasks, environments, and their parameters, resulting in more rigorous ways of measuring, comparing, and evaluating intelligent behavior.

A Systems Theory of Transfer Learning

This framework provides a formal, general systems framework for modeling transfer learning that offers a rigorous foundation for system design and analysis and avoids the detailed mathematics of learning theory or machine learning solution methods without excluding their consideration.

A Formal Model of Cognitive Synergy

“Cognitive synergy”– a dynamic in which multiple cognitive processes, cooperating to control the same cognitive system, assist each other in overcoming bottlenecks encountered during their internal

A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence, August 31, 1955

The 1956 Dartmouth summer research project on artificial intelligence was initiated by this August 31, 1955 proposal, authored by John McCarthy, Marvin Minsky, Nathaniel Rochester, and Claude Shannon, along with the short autobiographical statements of the proposers.

A theory of learning from different domains

A classifier-induced divergence measure that can be estimated from finite, unlabeled samples from the domains and shows how to choose the optimal combination of source and target error as a function of the divergence, the sample sizes of both domains, and the complexity of the hypothesis class.

System Definition, System Worldviews, and Systemness Characteristics

It is concluded that the various system worldviews offer useful perspectives for systems engineers, who should have the flexibility to accept the fact that different worldviews may be appropriate for different situations and be ready to adopt them as necessary.

Introduction to Cybernetics.

Abstract : This book contains the collected and unified material necessary for the presentation of such branches of modern cybernetics as the theory of electronic digital computers, theory of

A Categorical Characterization of General Automata

  • D. Rine
  • Mathematics
    Inf. Control.
  • 1971

Local Learning Algorithms

A single analysis suggests that neither kNN or RBF, nor nonlocal classifiers, achieve the best compromise between locality and capacity.

Abstract Systems Theory

Basic systems concepts via formalization, Structured terminal systems-Characterization, and goal-seeking system.