Computationally Efficient Forgetting via Base-Level Activation

Derbinsky, Nate; Laird, John E.

doi:10.1037/e557102013-030

Cited by 2 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper does not address the computational challenges associated with efficiently implementing these policies. Derbinsky and Laird (2012) present and evaluate algorithms for implementing forgetting via base-level activation.…”

Section: Discussionmentioning

confidence: 99%

Competence-Preserving Retention of Learned Knowledge in Soar's Working and Procedural Memories

Derbinsky¹,

Laird²

2012

PsycEXTRA Dataset

Self Cite

View full text Add to dashboard Cite

Effective management of learned knowledge is a challenge when modeling human-level behavior within complex, temporally extended tasks. This paper evaluates one approach to this problem: forgetting knowledge that is not in active use (as determined by base-level activation) and can likely be reconstructed if it becomes relevant. We apply this model for selective retention of learned knowledge to the working and procedural memories of Soar. When evaluated in simulated, robotic exploration and a competitive, multi-player game, these policies improve model reactivity and scaling while maintaining reasoning competence.

show abstract

Section: Discussionmentioning

confidence: 99%

Competence-Preserving Retention of Learned Knowledge in Soar's Working and Procedural Memories

Derbinsky¹,

Laird²

2012

PsycEXTRA Dataset

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thus alternative solutions include tapping into existing methods for large-scale data management and improving the retrieval algorithms. Both avenues have been explored, the former by Soar and ACT-R, which used PostgreSQL relational database to load concepts and relations from WordNet [118,126], and the latter by the Companions architecture [165]. Alternatively, SPA supports a biologically plausible model of associative memory capable of representing over 100K concepts in WordNet using a network of spiking neurons [111].…”

Section: Global Memorymentioning

confidence: 99%

40 years of cognitive architectures: core cognitive abilities and practical applications

2018

View full text Add to dashboard Cite

In this paper we present a broad overview of the last 40 years of research on cognitive architectures. To date, the number of existing architectures has reached several hundred, but most of the existing surveys do not reflect this growth and instead focus on a handful of well-established architectures. In this survey we aim to provide a more inclusive and highlevel overview of the research on cognitive architectures. Our final set of 84 architectures includes 49 that are still actively developed, and borrow from a diverse set of disciplines, spanning areas from psychoanalysis to neuroscience. To keep the length of this paper within reasonable limits we discuss only the core cognitive abilities, such as perception, attention mechanisms, action selection, memory, learning, reasoning and metareasoning. In order to assess the breadth of practical applications of cognitive architectures we present information on over 900 practical projects implemented using the cognitive architectures in our list. We use various visualization techniques to highlight the overall trends in the development of the field. In addition to summarizing the current state-of-the-art in the cognitive architecture research, this survey describes a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need more research with respect to their mechanistic counterparts and thus can further inform how cognitive science might progress.

show abstract

Computationally Efficient Forgetting via Base-Level Activation

Cited by 2 publications

References 4 publications

Competence-Preserving Retention of Learned Knowledge in Soar's Working and Procedural Memories

Competence-Preserving Retention of Learned Knowledge in Soar's Working and Procedural Memories

40 years of cognitive architectures: core cognitive abilities and practical applications

Contact Info

Product

Resources

About