Observations abound about the power of visual imagery in human intelligence, from how Nobel prize-winning physicists make their discoveries to how children understand bedtime stories. These observations raise an important question for cognitive science, which is, what are the computations taking place in someone’s mind when they use visual imagery? Answering this question is not easy and will require much continued research across the multiple disciplines of cognitive science. Here, we focus on a related and more circumscribed question from the perspective of artificial intelligence (AI): If you have an intelligent agent that uses visual imagery-based knowledge representations and reasoning operations, then what kinds of problem solving might be possible, and how would such problem solving work? We highlight recent progress in AI toward answering these questions in the domain of visuospatial reasoning, looking at a case study of how imagery-based artificial agents can solve visuospatial intelligence tests. In particular, we first examine several variations of imagery-based knowledge representations and problem-solving strategies that are sufficient for solving problems from the Raven’s Progressive Matrices intelligence test. We then look at how artificial agents, instead of being designed manually by AI researchers, might learn portions of their own knowledge and reasoning procedures more »
- Award ID(s):
- Publication Date:
- NSF-PAR ID:
- Journal Name:
- Proceedings of the National Academy of Sciences
- Page Range or eLocation-ID:
- p. 29390-29397
- Proceedings of the National Academy of Sciences
- Sponsoring Org:
- National Science Foundation
More Like this
In this paper, we present the Visuospatial Reasoning Environment for Experimentation (VREE). VREE provides a simulated environment where intelligent agents interact with virtual objects while solving different visuospatial reasoning tasks. This paper shows how VREE is valuable for studying the sufficiency of visual imagery approaches for a large number of visuospatial reasoning tasks as well as how diverse strategies can be represented and studied within a single task. We present results from computational experiments using VREE on the block design task and on numerous subtests from the Leiter-R test battery on nonverbal intelligence.
Not quite any way you slice it: How different analogical constructions affect Raven's Matrices performanceAnalogical reasoning fundamentally involves exploiting redundancy in a given task, but there are many different ways an intelligent agent can choose to define and exploit redundancy, often resulting in very different levels of task performance. We explore such variations in analogical reasoning within the domain of geometric matrix reasoning tasks, namely on the Raven’s Standard Progressive Matrices intelligence test. We show how different analogical constructions used by the same basic visual-imagery-based computational model—varying only in how they “slice” a matrix problem into parts and do search and optimization within/across these parts—achieve very different levels of test performance, ranging from 13/60 correct all the way up to 57/60 correct. Our findings suggest that the ability to select or build effective high-level analogical constructions can be as important as an agent’s competencies in low-level reasoning skills, which raises interesting open questions about the extent to which building the “right” analogies might contribute to individual differences in human matrix reasoning performance, and how intelligent agents might learn to build or select from among different analogical constructions in the first place.
Visuospatial reasoning refers to a diverse set of skills that involve thinking about space and time. An artificial agent with access to a sufficiently large set of visuospatial reasoning skills might be able to generalize its reasoning ability to an unprecedented expanse of tasks including portions of many popular intelligence tests. In this paper, we stress the importance of a developmental approach to the study of visuospatial reasoning, with an emphasis on fundamental skills. A comprehensive benchmark, with properties we outline in this paper including breadth, depth, explainability, and domain-specificity, would encourage and measure the genesis of such a skillset. Lacking an existing benchmark that satisfies these properties, we outline the design of a novel test in this paper. Such a benchmark would allow for expanding analysis of existing datasets’ and agents’ applicability to the problem of generalized visuospatial reasoning.
Abstract Axiomatic Design (AD) provides a powerful thinking framework for solving complex engineering problems through the concept of design domains and diligent mapping and decomposition between functional and physical domains. Despite this utility, AD is yet to be implemented for widespread use by design practitioners solving real world problems in industry and exists primarily in the realm of academia. This is due, in part, to a high level of design expertise and familiarity with its methodology required to apply the AD approach effectively. It is difficult to correctly identify, extract, and abstract top-level functional requirements (FRs) based on early-stage design research. Furthermore, guiding early-stage design by striving to maintain functional independence, the first Axiom, is difficult at a systems level without explicit methods of quantifying the relationship between high-level FRs and design parameters (DPs). To address these challenges, Artificial Intelligence (AI) methods, specifically in deep learning (DL) assisted Natural Language Processing (NLP), have been applied to represent design knowledge for machines to understand, and, following AD principles, support the practice of human designers. NLP-based question-answering is demonstrated to automate early-stage identification of FRs and to assist design decomposition by recursively mapping and traversing down along the FR-DP hierarchical structure. Functionalmore »
Today’s classrooms are remarkably different from those of yesteryear. In place of individual students responding to the teacher from neat rows of desks, one more typically finds students working in groups on projects, with a teacher circulating among groups. AI applications in learning have been slow to catch up, with most available technologies focusing on personalizing or adapting instruction to learners as isolated individuals. Meanwhile, an established science of Computer Supported Collaborative Learning has come to prominence, with clear implications for how collaborative learning could best be supported. In this contribution, I will consider how intelligence augmentation could evolve to support collaborative learning as well as three signature challenges of this work that could drive AI forward. In conceptualizing collaborative learning, Kirschner and Erkens (2013) provide a useful 3x3 framework in which there are three aspects of learning (cognitive, social and motivational), three levels (community, group/team, and individual) and three kinds of pedagogical supports (discourse-oriented, representation-oriented, and process-oriented). As they engage in this multiply complex space, teachers and learners are both learning to collaborate and collaborating to learn. Further, questions of equity arise as we consider who is able to participate and in which ways. Overall, this analysis helps usmore »