Analogical Learning of Visual/Conceptual Relationships in Sketches

AAAI Conferences

This paper explores the use of analogy to learn about properties of sketches. Sketches often convey conceptual relationships between entities via the visual relationships between their depictions in the sketch. Understanding these conventions is an important part of adapting to a user. This paper describes how learning by accumulating examples can be used to make suggestions about such relationships in new sketches. We describe how sketches are being used in Companion Cognitive Systems to illustrate one context in which this problem arises. We describe how existing cognitive simulations of analogical matching and retrieval are used to generate suggestions for new sketches based on analogies with prior sketches. Two experiments provide evidence as to the accuracy and coverage of this technique.


Companion Cognitive Systems: A step towards human-level AI

AAAI Conferences

We are developing Companion Cognitive Systems, a new kind of software that can be effectively treated as a collaborator. Aside from their potential utility, we believe this effort is important because it focuses on three key problems that must be solved to achieve human-level AI: Robust reasoning and learning, performance and longevity, and interactivity. We describe the ideas we are using to develop the first architecture for Companions: Analogical processing, grounded in cognitive science for reasoning and learning, a distributed agent architecture hosted on a cluster to achieve performance and longevity, and sketching and concept maps to provide interactivity.


Companion Cognitive Systems

AI Magazine

We are developing Companion Cognitive Systems, a new kind of software that can be effectively treated as a collaborator. Aside from their potential utility, we believe this effort is important because it focuses on three key problems that must be solved to achieve human-level AI: Robust reasoning and learning, interactivity, and longevity. We describe the ideas we are using to develop the first architecture for Companions: analogical processing, grounded in cognitive science for reasoning and learning, sketching and concept maps to improve interactivity, and a distributed agent architecture hosted on a cluster to achieve performance and longevity. We outline some results on learning by accumulating examples derived from our first experimental version. What is known about cognition has grown significantly, and communication between fields in cognitive science has catalyzed all of them. Largescale representational resources, such as WordNet, FrameNet, and Cyc, have become available so that one can build large knowledge systems without starting from scratch. Central processing units (CPUs) have become fast enough and memories large enough to tackle systems that could only be dreamed about previously. The confluence of these three factors suggest to us that the time is right for more ambitious projects, building integrated systems using the best available results from cognitive science. The effort we have embarked on to create Companion Cognitive Systems represents one such project. Let us start with our practical goals for Companions. The problems we face are growing more complex, but we are not becoming any smarter. Software can help, but often it becomes part of the problem by adding new layers of complexity. We need to bring software closer to us, improving conceptual bandwidth and having it adapt to us, rather than the other way around. Our vision is this: Companions will be software aide-de-camps, collaborators with their users. Companions will help their users work through complex arguments, automatically retrieving relevant precedents, providing cautions and counter-indications as well as supporting evidence. Companions will be capable of effective operation for weeks and months at a time, assimilating new information, generating and maintaining scenarios and predictions. Companions will continually adapt and learn, about the domains they are working in, their users, and themselves.


Companion Cognitive Systems: A Step toward Human-Level AI

AI Magazine

We are developing Companion Cognitive Systems, a new kind of software that can be effectively treated as a collaborator. Aside from their potential utility, we believe this effort is important because it focuses on three key problems that must be solved to achieve human-level AI: Robust reasoning and learning, interactivity, and longevity. We describe the ideas we are using to develop the first architecture for Companions: analogical processing, grounded in cognitive science for reasoning and learning, sketching and concept maps to improve interactivity, and a distributed agent architecture hosted on a cluster to achieve performance and longevity. We outline some results on learning by accumulating examples derived from our first experimental version.


An Analogy Ontology for Integrating Analogical Processing and First-principles Reasoning

AAAI Conferences

This paper describes an analogy ontology, a formal representation of some key ideas in analogical processing, that supports the integration of analogical processing with first-principles reasoners. The ontology is based on Gentner's structure-mapping theory, a psychological account of analogy and similarity. The semantics of the ontology are enforced via procedural attachment, using cognitive simulations of structure-mapping to provide analogical processing services. Queries that include analogical operations can be formulated in the same way as standard logical inference, and analogical processing systems in turn can call on the services of first-principles reasoners for creating cases and validating their conjectures. We illustrate the utility of the analogy ontology by demonstrating how it has been used in three systems: A crisis management analogical reasoner that answers questions about international incidents, a course of action analogical critiquer that provides feedback about military plans, and a comparison question-answering system for knowledge capture.