scholarly journals Analogy and Relational Representations in the Companion Cognitive Architecture

AI Magazine ◽  
2017 ◽  
Vol 38 (4) ◽  
pp. 34-42
Author(s):  
Kenneth D. Forbus ◽  
Thomas Hinrich
Keyword(s):  
Analogical Reasoning ◽  
Cognitive Architecture ◽  
Lessons Learned ◽  
Cognitive Systems ◽  
Open Problems ◽  
Systems Research ◽  
Software Social

The Companion cognitive architecture is aimed at reaching human-level AI by creating software social organisms, systems that interact with people using natural modalities, working and learning over extended periods of time as collaborators rather than tools. Our two central hypotheses about how to achieve this are (1) analogical reasoning and learning are central to cognition, and (2) qualitative representations provide a level of description that facilitates reasoning, learning, and communication. This paper discusses the evidence we have gathered supporting these hypotheses from our experiments with the Companion architecture. Although we are far from our ultimate goals, these experiments provide strong breadth for the utility of analogy and QR across a range of tasks. We also discuss three lessons learned and highlight three important open problems for cognitive systems research more broadly.

Attention and Consciousness in Intentional Action: Steps Toward Rich Artificial Agency

2020 ◽  
Vol 07 (01) ◽  
pp. 15-24
Author(s):  
Paul Bello ◽  
Will Bridewell
Keyword(s):  
Cognitive Architecture ◽  
Critical Role ◽  
Intentional Action ◽  
Lessons Learned ◽  
Psychological Explanation ◽  
Cognitive Systems ◽  
Artificial Agents ◽  
Human Machine Interaction ◽  
Machine Interaction ◽  
Insight Into

If artificial agents are to be created such that they occupy space in our social and cultural milieu, then we should expect them to be targets of folk psychological explanation. That is to say, their behavior ought to be explicable in terms of beliefs, desires, obligations, and especially intentions. Herein, we focus on the concept of intentional action, and especially its relationship to consciousness. After outlining some lessons learned from philosophy and psychology that give insight into the structure of intentional action, we find that attention plays a critical role in agency, and indeed, in the production of intentional action. We argue that the insights offered by the literature on agency and intentional action motivate a particular kind of computational cognitive architecture, and one that hasn’t been well-explicated or computationally fleshed out among the community of AI researchers and computational cognitive scientists who work on cognitive systems. To give a sense of what such a system might look like, we present the ARCADIA attention-driven cognitive system as first steps toward an architecture to support the type of agency that rich human–machine interaction will undoubtedly demand.

scholarly journals The Case for Explicit Ethical Agents

AI Magazine ◽  
2017 ◽  
Vol 38 (4) ◽  
pp. 57-64 ◽  
Author(s):  
Matthias Scheutz
Keyword(s):  
Cognitive Architecture ◽  
Ethical Reasoning ◽  
Social Contexts ◽  
Machine Ethics ◽  
Cognitive Systems ◽  
Human Society ◽  
Moral Principles ◽  
Ethical Competence ◽  
System Risk ◽  
Normative Expectations

Morality is a fundamentally human trait which permeates all levels of human society, from basic etiquette and normative expectations of social groups, to formalized legal principles upheld by societies. Hence, future interactive AI systems, in particular, cognitive systems on robots deployed in human settings, will have to meet human normative expectations, for otherwise these system risk causing harm. While the interest in “machine ethics” has increased rapidly in recent years, there are only very few current efforts in the cognitive systems community to investigate moral and ethical reasoning. And there is currently no cognitive architecture that has even rudimentary moral or ethical competence, i.e., the ability to judge situations based on moral principles such as norms and values and make morally and ethically sound decisions. We hence argue for the urgent need to instill moral and ethical competence in all cognitive system intended to be employed in human social contexts.

Relational Reasoning in a Neurally Plausible Cognitive Architecture

2005 ◽  
Vol 14 (3) ◽  
pp. 153-157 ◽  
Author(s):  
John E. Hummel ◽  
Keith J. Holyoak
Keyword(s):  
Analogical Reasoning ◽  
A Priori ◽  
Cognitive Architecture ◽  
Relational Reasoning ◽  
Natural Basis ◽  
Analogical Inference ◽  
Analogical Mapping ◽  
Design Requirements ◽  
Human Thinking ◽  
Propositional Structures

Human mental representations are both flexible and structured—properties that, together, present challenging design requirements for a model of human thinking. The Learning and Inference with Schemas and Analogies (LISA) model of analogical reasoning aims to achieve these properties within a neural network. The model represents both relations and objects as patterns of activation distributed over semantic units, integrating these representations into propositional structures using synchrony of firing. The resulting propositional structures serve as a natural basis for memory retrieval, analogical mapping, analogical inference, and schema induction. The model also provides an a priori account of the limitations of human working memory and can simulate the effects of various kinds of brain damage on thinking.

Rethinking the Comprehensive Test on Qualitative Reasoning for Designers

2013 ◽  
Author(s):  
Maryam Khorshidi ◽  
Jami J. Shah ◽  
Jay Woodward
Keyword(s):  
Time Allocation ◽  
Cognitive Skills ◽  
Analogical Reasoning ◽  
Divergent Thinking ◽  
Engineering Students ◽  
Deductive Reasoning ◽  
Qualitative Reasoning ◽  
Lessons Learned ◽  
Abductive Reasoning ◽  
Technical Problems

A battery of tests assessing the cognitive skills needed for the conceptual design is being developed. Tests on Divergent thinking and visual thinking are fully developed and validated. The first version of the qualitative reasoning test has also been developed; this paper focuses on the lessons learned from testing of the first version of the test (alpha version) and the improvements made to it since then. A number of problems were developed for each indicator of the qualitative reasoning skill (deductive reasoning, inductive reasoning, analogical reasoning, and abductive reasoning). Later, a protocol study was done with the problems to make sure that the problems assess the desired skills. The problems were also given to a randomly chosen population of undergraduate senior-level or graduate-level engineering students. Data was collected from the test results on the possible correlations between the problems (e.g. technical and non-technical problems); feedback on clarity, time allocation, and difficulty for each problem was also collected. Based on all of the observed correlations, the average performance of the test takers, and test parameters such as validity, reliability, etc. the beta version of the test is constructed.

Sign in / Sign up

Export Citation Format

Share Document