• Corpus ID: 11410634

Biologically Inspired Cognitive Architecture for Socially Competent Agents

  title={Biologically Inspired Cognitive Architecture for Socially Competent Agents},
  author={A. Samsonovich},
The challenge addressed here is to design a hybrid cognitive architecture that will possess the minimal Core Cognitive Competency (CCC) sufficient for the cognitive and social growth of an agent up to the human level of intelligence, based on autonomous learning. The approach is based on the integration of high-level symbolic (schema-based) and connectionist components at the top representational level, as described previously. The present work specifically addresses the mechanisms of… 

Figures and Tables from this paper

Schema formalism for the common model of cognition
  • A. Samsonovich
  • Computer Science
    Biologically Inspired Cognitive Architectures
  • 2018
A pragmatic path toward endowing virtually-embodied AIs with human-level linguistic capability
  • B. Goertzel
  • Biology
    2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
  • 2008
A pathway towards giving the NCE robust, ultimately human level natural language conversation capability is described, which starts via using the current system to instruct NCE-controlled agents in semiosis and gestural communication and continues via integration of a particular sort of hybrid rule-based/statistical NLP system.
Universal Learner as an Embryo of Computational Consciousness
  • A. Samsonovich
  • Computer Science
    AAAI Fall Symposium: AI and Consciousness
  • 2007
The purpose of the present work is to explain how a universal learner can be created and to discuss scientific and philosophical implications of emergent computational consciousness.
Toward a BICA-Model-Based Study of Cognition Using Brain Imaging Techniques
A Review of 40 Years of Cognitive Architecture Research: Core Cognitive Abilities and Practical Applications
A broad overview of the last 40 years of research on cognitive architectures, describing a variety of methods and ideas that have been tried and their relative success in modeling human cognitive abilities, as well as which aspects of cognitive behavior need more research with respect to their mechanistic counterparts and thus can further inform how cognitive science might progress.
Cognitive Map Dimensions of the Human Value System Extracted from Natural Language
The results suggest that the linguistically derived cognitive map of the human value system is language-invariant and, being closely related to psychometrically derived maps, is likely to reflect fundamental aspects of thehuman mind.


Computational Assessment of the `Magic' of Human Cognition
This work proposes several test scenarios and metrics that are adequate to assess cognitive features in computational agents and its possible solutions in one general paradigm of ontogenesis in virtual environment.
Human-Level Psychometrics for Cognitive Architectures
The present work introduces new test paradigms and metrics that are adequate to assess higher cognitive features in expected computational agents, while at the same time allowing for comparison with humans.
A General-Purpose Computational Model of the Conscious Mind
This work outlines general principles of a new approach to this task and illustrates them with detailed computational analysis based on a simple paradigm.
Meta-Cognitive Architecture for Team Agents
“self” is understood as a virtual character representing an agent as the subject of experience, as the target of attribution of experiences and deliberate actions performed by this agent, and can be represented as an element in an agent’s cognitive system and used for meta-cognitive processing.
Designing A Self-Aware Neuromorphic Hybrid
A top-level integration of symbolic and connectionist components of a cognitive architecture can be achieved through the blending of innovative concepts used in both components. i) On the
Towards Virtual Brains
In this chapter, we argue that computers are potentially capable of human-level cognition, including experiences involving emotions, creativity, fantasy, humor, etc. In addition, we maintain that
I argue that (subjective) consciousness is an aspect of an agent's intelligence, hence of its ability to deal adaptively with the world. In particular, it allows for the possibility of noting and
Engineering of Mind: An Introduction to the Science of Intelligent Systems
A Reference Model Architecture for Sensory Processing, Value Judgment, and Knowledge Representation for Engineering Unmanned Ground Vehicles and Future Possibilities is presented.
Introspective and elaborative processes in rational agents
  • C. Ortiz
  • Philosophy
    Annals of Mathematics and Artificial Intelligence
  • 2004
A new semantics for intention is presented that is both dynamic and causal in the sense that it is given in terms of the relation of an intention to both previous and subsequent mental states as well as to the choice of physical action.
Formalizing Collaborative Decision-making and Practical Reasoning in Multi-agent Systems
An abstract formal model of decision-making in a social setting that covers all aspects of the process, from recognition of a potential for cooperation t hrough to joint decision, and is formalized through a new, many-sorted, multi-modal logic.