Companion Cognitive Systems: Design Goals and Lessons Learned So Far

Forbus, Kenneth D.; Klenk, Matthew; Hinrichs, Thomas R.

doi:10.1109/mis.2009.71

Cited by 25 publications

(19 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Looking at the large scale models we have constructed using our models of matching, retrieval, and generalization, a common pattern can be found, one that is the basis for the Companion cognitive architecture (Forbus et al., ). In computer science, an architectural stack is a layering of systems that depend on each other.…”

Section: Our Proposal: Symbolic Representations and Structure‐mappingmentioning

confidence: 94%

See 1 more Smart Citation

Representation and Computation in Cognitive Models

Forbus

Liang

Rabkina

2017

Topics in Cognitive Science

Self Cite

View full text Add to dashboard Cite

One of the central issues in cognitive science is the nature of human representations. We argue that symbolic representations are essential for capturing human cognitive capabilities. We start by examining some common misconceptions found in discussions of representations and models. Next we examine evidence that symbolic representations are essential for capturing human cognitive capabilities, drawing on the analogy literature. Then we examine fundamental limitations of feature vectors and other distributed representations that, despite their recent successes on various practical problems, suggest that they are insufficient to capture many aspects of human cognition. After that, we describe the implications for cognitive architecture of our view that analogy is central, and we speculate on roles for hybrid approaches. We close with an analogy that might help bridge the gap.

show abstract

Section: Our Proposal: Symbolic Representations and Structure‐mappingmentioning

confidence: 94%

“…These component models have been incorporated into a cognitive architecture, the Companion cognitive architecture (Forbus, Klenk, & Hinrichs, 2009). This architecture is an exploration of the hypothesis that analogy and qualitative representations are essential to human cognition.…”

Section: Symbolic Relational Models Explain a Variety Of Psychologicamentioning

confidence: 99%

Representation and Computation in Cognitive Models

Forbus

Liang

Rabkina

2017

Topics in Cognitive Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…By using the OpenCyc ontology whenever possible, we reduce tailorability in our representations. We implemented TIMBER using the Companion cognitive architecture (Forbus, Klenk, & Hinrichs, 2009). In each trial, TIMBER starts with hand-coded domain knowledge pertaining to one or more students from Sherin et al, but no explanations have been constructed.…”

Section: Methodsmentioning

confidence: 99%

“…We implemented Timber using the Companion cognitive architecture (Forbus, Klenk, & Hinrichs, ). In each trial, Timber starts with hand‐coded domain knowledge pertaining to one or more students from Sherin et al., but no explanations have been constructed.…”

Section: Methodsmentioning

confidence: 99%

Representing, Running, and Revising Mental Models: A Computational Model

Friedman

Forbus²,

Sherin³

2017

Cognitive Science

View full text Add to dashboard Cite

People use commonsense science knowledge to flexibly explain, predict, and manipulate the world around them, yet we lack computational models of how this commonsense science knowledge is represented, acquired, utilized, and revised. This is an important challenge for cognitive science: Building higher order computational models in this area will help characterize one of the hallmarks of human reasoning, and it will allow us to build more robust reasoning systems. This paper presents a novel assembled coherence (AC) theory of human conceptual change, whereby people revise beliefs and mental models by constructing and evaluating explanations using fragmentary, globally inconsistent knowledge. We implement AC theory with Timber, a computational model of conceptual change that revises its beliefs and generates human-like explanations in commonsense science. Timber represents domain knowledge using predicate calculus and qualitative model fragments, and uses an abductive model formulation algorithm to construct competing explanations for phenomena. Timber then (a) scores competing explanations with respect to previously accepted beliefs, using a cost function based on simplicity and credibility, (b) identifies a low-cost, preferred explanation and accepts its constituent beliefs, and then (c) greedily alters previous explanation preferences to reduce global cost and thereby revise beliefs. Consistency is a soft constraint in Timber; it is biased to select explanations that share consistent beliefs, assumptions, and causal structure with its other, preferred explanations. In this paper, we use Timber to simulate the belief changes of students during clinical interviews about how the seasons change. We show that Timber produces and revises a sequence of explanations similar to those of the students, which supports the psychological plausibility of AC theory.

show abstract

“…It is stable, scales well (Forbus, Ferguson, and Gentner 1994), and is integrated with our other planning and reasoning facilities (Forbus, Klenk, and Hinrichs 2009).…”

Section: Analogical Transfermentioning

confidence: 99%

Transfer Learning through Analogy in Games

Hinrichs¹,

Forbus²

2011

AI Magazine

Self Cite

View full text Add to dashboard Cite

Articles70 AI MAGAZINE E ffectively transferring previously learned knowledge to a new domain is one of the hallmarks of human intelligence. This is the objective of transfer learning, in which transferred knowledge guides the learning process in a broad range of new situations. In near transfer, the source and target domains are very similar and solutions can be transferred almost verbatim. In far transfer, the domains may appear quite different and the knowledge to be transferred involves deeper shared abstractions. Thus transfer learning can be viewed as a compromise between the delayed generalization of instance-or casebased reasoning and the early generalization of classical machine learning.We have explored the use of analogy as a general approach to near and far transfer learning in domains ranging from physics problem solving to strategy games (Klenk and Forbus 2007;Hinrichs and Forbus 2007). Using the same basic analogical mechanism, we have found that the main differences between near and far transfer involve the amount of generalization that must be performed prior to transfer and the way that the matching process treats nonidentical predicates. We present here two extensions of our analogical matcher, minimal ascension and metamapping, that enable far transfer between representations with different relational vocabulary. Evidence for the effectiveness of these techniques is provided by a large-scale external evaluation, involving a substantial number of novel distant analogs.

show abstract

Companion Cognitive Systems: Design Goals and Lessons Learned So Far

Cited by 25 publications

References 7 publications

Representation and Computation in Cognitive Models

Representation and Computation in Cognitive Models

Representing, Running, and Revising Mental Models: A Computational Model

Transfer Learning through Analogy in Games

Contact Info

Product

Resources

About