How does Baum develop the idea of a chaining of models?

Baum has developed this idea by applying more rigorous property rules to govern the chaining of models and the apportionment of reward.

What are some examples of the types of strategies that can be used to augment learning?

Others look to augment strategies using implicit information about the context to adjust features of the learning such as the weightings (Aha 1989), or normalisation (Turney and Halasz 1993).

Open AccessJournal Article10.2139/SSRN.259847

Learning Appropriate Contexts

Q: What is the purpose of this paper?

This paper seeks to make some practical proposals as to how notions of conditions of applicability and then contexts themselves can be introduced into evolutionary computing.

Bruce Edmonds

- 01 Feb 2001

- Social Science Research Network

TL;DR: In this paper, it is argued that for context to be fully learnable, a further step of abstraction is necessary, and some principles of learning to identify useful contexts are proposed.

Abstract: Genetic Programming is extended so that the solutions being evolved do so in the context of local domains within the total problem domain. This produces a situation where different "species" of solution develop to exploit different "niches" of the problem - indicating exploitable solutions. It is argued that for context to be fully learnable a further step of abstraction is necessary. Such contexts abstracted from clusters of solution/model domains make sense of the problem of how to identify when it is the content of a model is wrong and when it is the context. Some principles of learning to identify useful contexts are proposed.

AI Agents for this Paper

Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps

Most frequently asked questions

1. What are the contributions in "Learning appropriate contexts" ?

In this paper, the authors make some practical proposals as to how notions of conditions of applicability and then contexts themselves can be introduced into evolutionary computing.

2. What is the effect of the descendants of the models?

Then as they produce descendants with variations, these descendants compete with them for problem space and the coverage of any particular model equals out.

3. What is the step to take to make a context?

There is still a step to take in order for it to be truly “context” that is being utilised – a collection of conditions of application become a context if it is sensible to abstract them as a coherent unit.

4. What are the options for a model to be able to identify the source of error?

They include: 1. Changing the model content (either by a minor elaboration or parameteradjustment or by a more radical restructuring); 2. Adjusting the conditions of application so as to exclude the domain where themodel did not work; 3. Making the predictions of the model less precise so as to allow for the error; 4. Finally, and most radically it may be necessary to change the language/basis ofthe model formulation itself.

Fig. 5. The Average Fitness of Models in the four runs

Fig. 4. The problem function – the number of sunspots

Citations

•Proceedings Article•10.1145/545056.545105

Learning and exploiting context in agents

Bruce Edmonds

- 15 Jul 2002

TL;DR: The algorithm is described and the agents compared with agents that learn and apply knowledge in a generic way within an artificial stock market and the potential for context as a principled manner of closely integrating crisp reasoning and fuzzy learning is discussed.

...read moreread less

Using Localised ‘Gossip’ to Structure Distributed Learning

Bruce Edmonds

- 01 Jan 2005

TL;DR: This approach is compared to the equivalent global evolutionary computation approach with respect to predicting theoccurence of heart disease in the Cleveland data set and greatly outperforms the global approach, but the space of attributes within which this evolutionary process occurs can effect its efficiency.

...read moreread less

Contextualizing observational data for modeling human performance

Viet Trinh

- 01 Jan 2009

TL;DR: This research proposes two contextualization algorithms: Contextualized Fuzzy ART (CFA) and Context Partitioning and Clustering (COPAC).

...read moreread less

Book Chapter•10.1007/978-1-4939-1887-4_18

Contextual Cognition in Social Simulation

Bruce Edmonds

- 01 Jan 2014

TL;DR: A principled way is proposed, using cognitive context, of integrating machine learning and reasoning processes into a single cognitive model suitable for use in social simulation, which is not only particularly suitable for social agents and their coordination but solves several problems at once.

...read moreread less

Integrating Domain Expertise With Aggregate Data Using Evolutionary Computation

Bruce Edmonds

- 01 Jan 2002

References

•Book

Adaptation in natural and artificial systems

John H. Holland

- 01 Jan 1975

TL;DR: Names of founding work in the area of Adaptation and modiication, which aims to mimic biological optimization, and some (Non-GA) branches of AI.

...read moreread less

40.3K

Book•10.7551/MITPRESS/1090.001.0001

Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence

John H. Holland

- 01 May 1992

TL;DR: Initially applying his concepts to simply defined artificial systems with limited numbers of parameters, Holland goes on to explore their use in the study of a wide range of complex, naturally occuring processes, concentrating on systems having multiple factors that interact in nonlinear ways.

...read moreread less

16.6K

•Book

Genetic Programming: On the Programming of Computers by Means of Natural Selection

John R. Koza

- 01 Jan 1992

TL;DR: This book discusses the evolution of architecture, primitive functions, terminals, sufficiency, and closure, and the role of representation and the lens effect in genetic programming.

...read moreread less

15K

•Journal Article•10.1037/0033-295X.103.4.650

Reasoning the fast and frugal way: models of bounded rationality.

Gerd Gigerenzer, +1 more

- 01 Jan 1996

- Psychological Review

TL;DR: The authors have proposed a family of algorithms based on a simple psychological mechanism: one-reason decision making, and found that these fast and frugal algorithms violate fundamental tenets of classical rationality: they neither look up nor integrate all information.

...read moreread less

3.5K

•Journal Article•10.1016/0010-0277(93)90058-4

Learning and development in neural networks: the importance of starting small

Jeffrey L. Elman

- 01 Jul 1993

- Cognition

TL;DR: Possible synergistic interactions between maturational change and the ability to learn a complex domain (language) as investigated in connectionist networks suggest that developmental restrictions on resources may constitute a necessary prerequisite for mastering certain complex domains.

...read moreread less

2.1K

...

Expand

Learning Appropriate Contexts

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What are the contributions in "Learning appropriate contexts" ?

2. What is the effect of the descendants of the models?

3. What is the step to take to make a context?

4. What are the options for a model to be able to identify the source of error?

5. How does Baum develop the idea of a chaining of models?

6. What are some examples of the types of strategies that can be used to augment learning?

7. What is the purpose of this paper?

Figures

Citations

Learning and exploiting context in agents

Using Localised ‘Gossip’ to Structure Distributed Learning

Contextualizing observational data for modeling human performance

Contextual Cognition in Social Simulation

Integrating Domain Expertise With Aggregate Data Using Evolutionary Computation

References

Adaptation in natural and artificial systems

Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence

Genetic Programming: On the Programming of Computers by Means of Natural Selection

Reasoning the fast and frugal way: models of bounded rationality.

Learning and development in neural networks: the importance of starting small

Related Papers (5)

Exploring Computational Mechanismfor Contexts.

Learning and exploiting context in agents

Towards context-aware propagators: language constructs for context-aware adaptation dependencies

Domains and context: First steps towards managing diversity in knowledge

Explanation-based learning: its role in problem-solving