Multimodal Cognitive Architecture: Making Perception More Central to Intelligent Behavior

AAAI Conferences

I propose that the notion of cognitive state be broadened from the current predicate-symbolic, Language-of-Thought framework to a multi-modal one, where perception and kinesthetic modalities participate in thinking. In contrast to the roles assigned to perception and motor activities as modules external to central cognition in the currently dominant theories in AI and Cognitive Science, in the proposed approach, central cognition incorporates parts of the perceptual machinery. I motivate and describe the proposal schematically, and describe the implementation of a bimodal version in which a diagrammatic representation component is added to the cognitive state. The proposal explains our rich multimodal internal experience, and can be a key step in the realization of embodied agents. The proposed multimodal cognitive state can significantly enhance the agent's problem solving. Note: Memory, as well as the information retrieved from memory and from perception, represented in a predicate-symbolic form.



SS93-01-021.pdf

AAAI Conferences

A CASE-BASED MODEL OF CREATIVITY SCOT'[" R. TURNER Department of Computer Science University of California, Los Angeles Los Angeles CA 90024 USA Abstract Creativity - creating new solutions to problems - is an integral part of the problem-solving process. This paper presents a cognitive model of creativity in which a case-based problem-solver is augmented with (1) a creative drive and (2) a set of creativity heuristics. New solutions are discovered by solving a slightly different problem and adapting that solution to the original problem. By repeating this process, a creative problem-solver can discover new solutions that are novel, useful and very different from known solutions. This model has been implemented in a computer program called MINSTREL. MINSTREL has been used for planning and problem-solving, to tell stories, and to invent mechanical devices. 1 Introduction Creativity is an important element of human cognition. We all invent on a daily basis: we fix cars using spare change and bailing wire, invent jokes based on the latest domestic crisis, and make up bedtime stories for our children. The ability to invent original, useful solutions to problems is a fundamental process of human thought. To understand human cognition, we must understand the processes of creativity: the goals that drive people to create and the mechanisms they use to invent novel and useful solutions to their problems. This paper presents a model of creative reasoning as an extension to case-based problem-solving.


How "intelligent" can Artificial Intelligence get?

#artificialintelligence

This post is the second in a series of three posts, each of which discuss the fundamental concepts of Artificial Intelligence. In our first post we discussed AI definitions, helping our readers to understand the basic concepts behind AI, giving them the tools required to sift through the many AI articles out there and form their own opinion. In this second post, we will discuss several notions which are important in understanding the limits of AI. Figure 1: How intelligent can Artificial Intelligence get? When we speak about how far AI can go, there are two "philosophies": strong AI and weak AI. The most commonly followed philosophy is that of weak AI, which means that machines can manifest certain intelligent behavior to solve specific (hard) tasks, but that they will never equal the human mind.


Towards a Quantum-Like Cognitive Architecture for Decision-Making

arXiv.org Artificial Intelligence

We propose an alternative and unifying framework for decision-making that, by using quantum mechanics, provides more generalised cognitive and decision models with the ability to represent more information than classical models. This framework can accommodate and predict several cognitive biases reported in Lieder & Griffiths without heavy reliance on heuristics nor on assumptions of the computational resources of the mind. Expected utility theory and classical probabilities tell us what people should do if employing traditionally rational thought, but do not tell us what people do in reality (Machina, 2009). Under this principle, L&G propose an architecture for cognition that can serve as an intermediary layer between Neuroscience and Computation. Whilst instances where large expenditures of cognitive resources occur are theoretically alluded to, the model primarily assumes a preference for fast, heuristic-based processing.