Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Discussion
Experimental Studies
Conclusions
References
All Topics
Computer Science
Artificial Intelligence

On developmental mental architectures

Profile image of Juyang WengJuyang Weng

2007, Neurocomputing

https://doi.org/10.1016/J.NEUCOM.2006.07.017
visibility

…

description

21 pages

link

1 file

Abstract

This paper presents a computational theory of developmental mental architectures for artificial and natural systems, motivated by neuroscience. The work is an attempt to approximately model biological mental architectures using mathematical tools. Six types of architecture are presented, beginning with the observation-driven Markov decision process as Type-1. From Type-1 to Type-6, the architecture progressively becomes more complete toward the necessary

Related papers

Cognitive Architectures
Paul Thagard

2012

A cognitive architecture is a general proposal about the representations and processes that produce intelligent thought. Cognitive architectures have primarily been used to explain important aspects of human thinking such as problem solving, memory, and learning. But they can also be used as blueprints for designing computers and robots that possess some of the cognitive abilities of humans. The most influential cognitive architectures that have been developed are either rule-based, using if-then rules and procedures that operate on them to explain thinking, or connectionist, using artificial neural networks. This chapter will describe the central structures and processes of these two kind of architectures, and review how well they succeed as general theories of mental processing. I argue that advances in neuroscience hold the promise for producing a general cognitive theory that encompasses the advantages of both rule-based and connectionist architectures.

View PDFchevron_right
EVOLVABLE ARCHITECTURES FOR HUMANLIKE MINDS
Aaron Sloman

2000

There are many approaches to the study of mind, and much ambiguity in the use of words like 'emotion' and 'consciousness'. This paper adopts the design stance and attempts to understand human minds as information processing virtual machines with a complex multi-level architecture whose components evolved at different times and perform different sorts of functions. A multi-disciplinary perspective combining ideas from engineering as well as several sciences helps to constrain the proposed architecture. Variations in the architecture should accommodate infants and adults, normal and pathological cases, and also animals. An analysis of states and processes that each architecture supports provides a new framework for systematically generating concepts of various kinds of mental phenomena. This framework can be used to refine and extend familiar concepts of mind, providing a new, richer, more precise theory-based collection of concepts. Within this unifying framework we hope to explain the diversity of definitions and theories and move towards deeper explanatory theories and more powerful and realistic artificial models, for use in many applications, including education and entertainment.

View PDFchevron_right
Designing Artificial Cognitive Architectures: Brain Inspired or Biologically Inspired? Designing Artificial Cognitive Architectures: Brain Inspired or Biologically Inspired
Emanuel Diamant

Procedia Computer Science 145 , 153–157, 2018

Artificial Neural Networks (ANNs) were devised as a tool for Artificial Intelligence (AI) design implementations. However, it was soon became obvious that they are unable to fulfil their duties. The fully autonomous way of ANNs working, precluded from any human intervention or supervision, deprived of any theoretical underpinning, leads to a strange state of affairs, when ANN designers cannot explain why and how they achieve their amazing and remarkable results. Therefore, contemporary Artificial Intelligence R&D looks more like a Modern Alchemy enterprise rather than a respected scientific or technological undertaking. On the other hand, modern biological science posits that intelligence can be distinguished not only in human brains. Intelligence today is considered as a fundamental property of each and every living being. Therefore, lower simplified forms of natural intelligence are more suitable for investigation and further replication in artificial cognitive architectures. Abstract Artificial Neural Networks (ANNs) were devised as a tool for Artificial Intelligence (AI) design implementations. However, it was soon became obvious that they are unable to fulfil their duties. The fully autonomous way of ANNs working, precluded from any human intervention or supervision, deprived of any theoretical underpinning, leads to a strange state of affairs, when ANN designers cannot explain why and how they achieve their amazing and remarkable results. Therefore, contemporary Artificial Intelligence R&D looks more like a Modern Alchemy enterprise rather than a respected scientific or technological undertaking. On the other hand, modern biological science posits that intelligence can be distinguished not only in human brains. Intelligence today is considered as a fundamental property of each and every living being. Therefore, lower simplified forms of natural intelligence are more suitable for investigation and further replication in artificial cognitive architectures.

View PDFchevron_right
Biologically Inspired Cognitive Architectures 2010: Proceedings of the First Annual Meeting of the BICA Society
Roberto Pirrone

2010

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 perception, voluntary action and social communication based on the given formalism of schemas. Social competency appears to be vital for CCC.

View PDFchevron_right
How to Engineer Biologically Inspired Cognitive Architectures
Massimo Cossentino

Advances in Intelligent Systems and Computing, 2013

Biologically inspired cognitive architectures are complex systems where different modules of cognition interact in order to reach the global goals of the system in a changing environment. Engineering and modeling this kind of systems is a hard task due to the lack of techniques for developing and implementing features like learning, knowledge, experience, memory, adaptivity in an inter-modular fashion. We propose a new concept of intelligent agent as abstraction for developing biologically cognitive architectures.

View PDFchevron_right
Towards Integrated Biologically Inspired Cognitive Architecture s
Catalin Buiu

robots.ics.pub.ro

A cognitive architecture includes those aspects of a cognitive system that are relatively invariant across time, domains, and individuals. Biological systems are meaningful sources inspiration on how to design and implement such architectures. Various neuroscience theories and principles have been implemented in specific cognitive architectures, but the resulted abilities are rather specialized for different modal problems than integrated. This paper presents a research initiative funded by the Romanian Government aiming at developing an integrated cognitive architecture with biological inspirations. One of the proposed innovations brought by this endeavor is that it proposes the use of symbolic and numerical P systems (or membrane computing) which are computational models of the biomembrane system of a living cell. A first application of P systems in controlling mobile robots is presented.

View PDFchevron_right
A Survey of Artificial Cognitive Systems: Implications for the Autonomous Development of Mental Capabilities in Computational Agents
David Vernon

IEEE Transactions on Evolutionary Computation, 2000

This survey presents an overview of the autonomous development of mental capabilities in computational agents. It does so based on a characterization of cognitive systems as systems which exhibit adaptive, anticipatory, and purposive goal-directed behavior. We present a broad survey of the various paradigms of cognition, addressing cognitivist (physical symbol systems) approaches, emergent systems approaches, encompassing connectionist, dynamical, and enactive systems, and also efforts to combine the two in hybrid systems. We then review several cognitive architectures drawn from these paradigms. In each of these areas, we highlight the implications and attendant problems of adopting a developmental approach, both from phylogenetic and ontogenetic points of view. We conclude with a summary of the key architectural features that systems capable of autonomous development of mental capabilities should exhibit.

View PDFchevron_right
Designing Artificial Cognitive Architectures: Brain Inspired or Biologically Inspired?
Emanuel Diamant

2018

Artificial Neural Networks (ANNs) were devised as a tool for Artificial Intelligence design implementations. However, it was soon became obvious that they are unable to fulfill their duties. The fully autonomous way of ANNs working, precluded from any human intervention or supervision, deprived of any theoretical underpinning, leads to a strange state of affairs, when ANN designers cannot explain why and how they achieve their amazing and remarkable results. Therefore, contemporary Artificial Intelligence R&D looks more like a Modern Alchemy enterprise rather than a respected scientific or technological undertaking. On the other hand, modern biological science posits that intelligence can be distinguished not only in human brains. Intelligence today is considered as a fundamental property of each and every living being. Therefore, lower simplified forms of natural intelligence are more suitable for investigation and further replication in artificial cognitive architectures.

View PDFchevron_right
Computational Autonomous Mental Development
Ida Stockman

2000

A new synthesis of the neural, behavioral, and computer sciences is on the horizon. The topic that promises to unite these disparate fields is computational autonomous mental development. The term "mental" refers to cognitive, behavioral and other mental skills that are exhibited by humans, higher animals and artificial systems. Computational autonomous mental development refers to the computational process by which a brain-like machine, natural or artificial, develops mental skills under the guidance of an intrinsic developmental program and through its own autonomous activities using its sensors and effectors to interact with its environment. The developmental program for an animal resides in the genes as a result of many generations of evolution; while that for a machine is initially programmed into the machine by humans but the environment changes the ways that the developmental program operates. The synthesis is inspired by new discoveries in neuroscience that highlight the exquisite plasticity of the brain with experience through infancy and adulthood, by new theories and computational modeling of human cognitive development, and by methodological and computational advances in AI and robotics that make it possible for machines to autonomously develop their own intelligence. Potentially, there are enormous benefits as a result of this synthesis: For behavioral and neural scientists, it promises a deeper, more precise and more systematic understanding about the ways our brain works through the computational study of its developmental processes. For the engineering and computer sciences, there is the vision of greatly enhanced capability for machines to interact with humans and to process information to a degree that requires kinds of machine intelligence other than those possible before.

View PDFchevron_right
Mind Architecture and Brain Architecture
Camilo J . Cela-Conde

Biology & Philosophy

Can we understand brains and minds of humans and other animals well enough to build convincing functional robot models? Premisses:

View PDFchevron_right

References (56)

  1. J.S. Albus, Outline for a theory of intelligence, IEEE Trans. Syst. Man Cybern. 21 (3) (1991) 473-509.
  2. N. Almassy, G.M. Edelman, O. Sporns, Behavioral constraints in the development of neural properties: a cortical model embedded in a real-world device, Cereb. Cortex 8 (4) (1998) 346-361.
  3. J.R. Anderson, Rules of the Mind, Lawrence Erlbaum, Mahwah, NJ, 1993.
  4. R. Baillargeon, Object permanance in 3.5 and 4.5-month-old infants, Dev. Psychol. 23 (1987) 655-664.
  5. L. Birnbaum, M. Brand, P. Cooper, Looking for trouble: using causal semantics to direct focus of attention, in: Proceedings of the Fourth International Conference on Computer Vision, 1993, pp. 49-56.
  6. R.A. Brooks, A robust layered control system for a mobile robot, IEEE J. Robot. Autom. 2 (1) (1986) 14-23.
  7. D.R. Cox, Statistical analysis of time series: some recent develop- ments, Scand. J. Statist. 8 (2) (1981) 93-115.
  8. J.L. Elman, Learning and development in neural networks: The importance of starting small, Cognition 48 (1) (1993) 71-99.
  9. J.A. Feldman, D.H. Ballard, Connectionist models and their properties, Cognitive Sci. 6 (3) (1982) 205-254.
  10. X. Huang, J. Weng, Novelty and reinforcement learning in the value system of developmental robots, in: Proceedings of the Second International Workshop on Epigenetic Robotics (EPIROB'02), Edinburgh, Scotland, August 10-11, 2002, pp. 47-55.
  11. X. Huang, J. Weng, Value system development for a robot, in: Proceedings of the 2004 International Joint Conference on Neural Networks, July 26-29, 2004.
  12. W.S. Hwang, J. Weng, Hierarchical discriminant regression, IEEE Trans. Pattern Anal. Mach. Intell. 22 (11) (2000) 1277-1293.
  13. P.N. Johnson-Laird, Human and Machine Thinking, Lawrence Erlbaum, Hillsdale, NJ, 1993.
  14. L.P. Kaelbling, M.L. Littman, A.W. Moore, Reinforcement learning: a survey, J. Artif. Intell. Res. 4 (1996) 237-285.
  15. E.R. Kandel, J.H. Schwartz, T.M. Jessell (Eds.), Principles of Neural Science, fourth Ed., McGraw-Hill, New York, 2000.
  16. B. Kolb, I.Q. Whishaw, Fundamentals of Human Neuropsychology, third Ed., Freeman, New York, 1990.
  17. J.E. Laird, A. Newell, P.S. Rosenbloom, Soar: An architecture for general intelligence, Artif. Intell. 33 (1987) 1-64.
  18. A.R. Luria, The Working Brain, Penguin, Harmondsworth, England, 1973.
  19. D.W. Massoro, M.M. Cohen, L.A. Thompson, Visible language in speech perception: Lipreading and reading, Visible Language 22 (1) (1988) 8-31.
  20. D.E. Meyer, D.E. Kieras, A computational theory of executive cognitive processes and multiple-task performance: Part 1 basic mechanisms, Psychol. Rev. 104 (1997) 2-65.
  21. D.E. Meyer, D.E. Kieras, A computational theory of executive cognitive processes and multiple-task performance: Part 2 accounts of psychological refractory-period phenomena, Psychol. Rev. 104 (1997) 749-791.
  22. M. Minsky, Private Communication, 1999.
  23. U. Neisser, Cognitive Psychology, Appleton-Century-Crofts, New York, 1967.
  24. B.A. Olshansen, C.H. Anderson, D.C. Van Essen, A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information, J. Neurosci. 13 (11) (1993) 4700-4719.
  25. D.N. Pandya, B. Seltzer, Association areas of the cerebral cortex, Trends Neurosci. 5 (1982) 386-390.
  26. V. Pratt, Thinking Machines, Basil Blackwell, Oxford UK, 1987.
  27. M.L. Puterman, Markov Decision Processes, Wiley, New York, 1994.
  28. L.R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition, Proc. IEEE 77 (2) (1989) 257-286.
  29. D. Reisfeld, H. Woldson, Y. Yeshurun, Context-free attentional operators: the generalized symmetry transform, Int. J. Comput. Vision 14 (1995) 119-130.
  30. J.E. Richards (Ed.), Cognitive Neuroscience of Attention: A Developmental Perspective, Lawrence Erlbaum, Mahwah, New Jersey, 1998.
  31. A.J. Rudnicky, A.G. Hauptmann, K.F. Lee, Survey of current speech technology, Commun. ACM 37 (3) (1994) 52-57.
  32. L.R. Squire, E.R. Kandel, Memory: From Mind to Molecules, Scientific American Library, New York, 1999.
  33. R.J. Sternberg (Ed.), Thinking and Problem Solving, Academic Press, San Diego, California, 1994 (Chapters 1 and 2).
  34. R.S. Sutton, A. Barto, Reinforcement Learning, MIT Press, Cam- bridge, MA, 1998.
  35. J.K. Tsotsos, A 'complexity level' analysis of immediate vision, Int. J. Comput. Vision 1 (4) (1988) 303-320.
  36. J.K. Tsotsos, Analyzing vision at the complexity level, Behav. Brain Sci. 13 (1990) 423-469.
  37. A.M. Turing, Computing machinery and intelligence, Mind 59 (1950) 433-460.
  38. A. Van der Heijden, Selective Attention in Vision, Routledge, New York, 1992.
  39. L.S. Vygotsky, Thought and Language, MIT Press, Cambridge, MA, 1962 trans. E. Hanfmann, G. Vakar.
  40. A. Waibel, K. Lee, Readings in Speech Recognition, Morgan Kaufmann, San Mateo, CA, 1990.
  41. C. Watkins, P. Dayan, Q-learning, Mach. Learn. 8 (1992) 279-292.
  42. J. Weng, A theory for mentally developing robots, in: Proceedings of the IEEE Second International Conference on Development and Learning (ICDL 2002), June 12-15, MIT, Cambridge, MA, 2002, pp. 131-140.
  43. J. Weng, Developmental robotics: Theory and experiments, Int. J. Humanoid Robot. 1 (2) (2004) 199-235.
  44. J. Weng, W. Hwang, Online image classification using IHDR, Int. J. Document Anal. Recognition 5 (2-3) (2002) 118-125.
  45. J. Weng, W.S. Hwang, An incremental learning algorithm with automatically derived discriminating features, in: Proceedings of the Asian Conference on Computer Vision, Taipei, Taiwan, January 8-9, 2000, pp. 426-431.
  46. J. Weng, W.S. Hwang, Y. Zhang, C. Evans, Developmental robots: Theory, method and experimental results, in: Proceedings of the Second International Conference on Humanoid Robots, Tokyo, Japan, October 8-9, IEEE Press, 1999, pp. 57-64.
  47. J. Weng, J. McClelland, A. Pentland, O. Sporns, I. Stockman, M. Sur, E. Thelen, Autonomous mental development by robots and animals, Science 291 (5504) (2001) 599-600.
  48. J. Weng, I. Stockman, Autonomous mental development: Workshop on development and learning, Artif. Intell. Magazine 23 (2) (2002) 95-98.
  49. J. Weng, Y. Zhang, Y. Chen, Developing early senses about the world: 'object permanence' and visuoauditory real-time learning, in: Proceedings of the International Joint Conference on Neural Networks, Portland, Oregon, July 20-24, 2003.
  50. D.J. Wood, J.S. Bruner, G. Ross, The role of tutoring in problem- solving, J. Child Psychol. Psychiatry (1976) 89-100.
  51. N. Zhang, J. Weng, A developing sensory mapping for robots, in: Proceedings of the IEEE Second International Conference on Development and Learning (ICDL 2002), June 12-15, MIT, Cam- bridge, MA, 2002, pp. 13-20.
  52. N. Zhang, J. Weng, X. Huang, Progress in outdoor navigation by the SAIL developmental robot, in: Proceedings of the SPIE International Symposium on Intelligent Systems and Advanced Manufacturing, vol. 4573, October 28-November 2, Newton, MA, 2001.
  53. Y. Zhang, J. Weng, Grounded auditory development by a develop- mental robot, in: Proceedings of the INNS-IEEE International Joint Conference on Neural Networks, Washington, DC, July 14-19, 2001, pp. 1059-1064.
  54. Y. Zhang, J. Weng, Action chaining by a developmental robot with a value system, in: Proceedings of the IEEE Second International Conference on Development and Learning (ICDL 2002), June 12-15, MIT, Cambridge, MA, 2002, pp. 53-60.
  55. Y. Zhang, J. Weng, Conjunctive visual and auditory development via real-time dialogue, in: Proceedings of the Third International Workshop on Epigenetic Robotics (EPIROB'03), Boston, MA, August 4-5, 2003, pp. 974-980.
  56. Juyang (John) Weng received his Ph.D. degree in Computer Science from University of Illinois, Urbana, IL USA, January 1989. His research interests include mental architectures, computa- tional neuroscience, mental development, biolo- gically inspired neural systems, vision, audition, touch, human-machine multimodal interface, and intelligent robots. He is the author or coauthor of over 180 reviewed research articles and book chapters published in books, journals, conferences and workshops. He is an editor-in-chief of International Journal of Humanoid Robotics and the founding Chairman of the Governing Board of the multidisciplinary International Conferences on Development and Learning (ICDL) (http://cogsci.ucsd.edu/$triesch/icdl/). He was the founding chairman of the Autonomous Mental Development Technical Committee of the IEEE Computational Intelligence Society (2004-2005), an associate editor of the IEEE Trans. on Pattern Recognition and Machine Intelligence, an associate editor of the IEEE Trans. on Image Processing, a program chairman of the NSF/DARPA Workshop on Development and Learning (WDL), held April 2000 at Michigan State University (MSU), East Lansing, MI (http://www.cse.msu.edu/dl/), and a program chairman of the 2nd International Conference on Development and Learning (ICDL02), held at Massachusetts Institute of Technology, Cambridge, MA, June 2002 (http://www.egr.msu.edu/icdl02/). He in- itiated and supervised the SAIL (Self-organizing Autonomous Incre- mental Learner) and Dav projects, in which he and his coworkers have designed and custom built their SAIL and Dav robots for research on robotic computational realization of autonomous mental development. More detail is available on line at http://www.cse.msu.edu/weng/.

Related papers

A Theory of Developmental Architecture
Juyang Weng

2004

This paper presents a theory of developmental mental architecture primarily for robots. Six types of architecture are presented, starting with the observation-driven Markov decision process as Type-1. From Type-1 to Type-6, the architecture progressively becomes more complete toward the necessary functions of the autonomously developing agent. Properties of each architecture type are presented.

View PDFchevron_right
An impressive and ambitious new cognitive architecture that integrates cognitive modeling with biological reality
Curt Carlson

The scientific study of cognition can be broken down into a series of levels in a hierarchy, but what follows is by no means an exhaustive list. Basic empiricism, the testing of hypotheses with observable data, is toward the bottom. Next up the ladder is theory-driven empiricism, according to which hypotheses are grounded in a particular theoretical approach, and results can serve as a piece of an overarching puzzle or framework. Another level up is the place for quantitative modeling, wherein theories are stated in highly specified and highly testable terms. Such models can be fit to data, and the successes or failures of such model fitting tend to direct the model toward ever more improved approximations of some aspect of cognition or behavior.

View PDFchevron_right
Design for a Darwinian Brain: Part 2. Cognitive Architecture
Alexander Churchill

The accumulation of adaptations in an open-ended manner during lifetime learning is a holy grail in reinforcement learning, intrinsic motivation, artificial curiosity, and developmental robotics. We present a design for a cognitive architecture that is capable of specifying an unlimited range of behaviors. We then give examples of how it can stochastically explore an interesting space of adjacent possible behaviors. There are two main novelties; the first is a proper definition of the fitness of self-generated games such that interesting games are expected to evolve. The second is a modular and evolvable behavior language that has systematicity, productivity, and compositionality, i.e. it is a physical symbol system. A part of the architecture has already been implemented on a humanoid robot.

View PDFchevron_right
Markov Brains: A Technical Introduction
Larissa Albantakis

2017

Markov Brains are a class of evolvable artificial neural networks (ANN). They differ from conventional ANNs in many aspects, but the key difference is that instead of a layered architecture, with each node performing the same function, Markov Brains are networks built from individual computational components. These computational components interact with each other, receive inputs from sensors, and control motor outputs. The function of the computational components, their connections to each other, as well as connections to sensors and motors are all subject to evolutionary optimization. Here we describe in detail how a Markov Brain works, what techniques can be used to study them, and how they can be evolved.

View PDFchevron_right
Biologically Inspired Cognitive Architectures 2012
Roberto Pirrone, Kamilla J

Advances in Intelligent Systems and Computing, 2013

The challenge of creating a real-life computational equivalent of the human mind requires that we better understand at a computational level how natural intelligent systems develop their cognitive and learning functions. In recent years, biologically inspired cognitive architectures have emerged as a powerful new approach toward gaining this kind of understanding (here “biologically inspired” is understood broadly as “brain-mind inspired”). Still, despite impressive successes and growing interest in BICA, wide gaps separate ...

View PDFchevron_right

Related topics

  • Engineering
  • Computer Science
  • Computability Theory
  • Language Acquisition
  • Developmental Robotics
  • Markov Decision Process
  • Autonomous Mental Development
  • Psychology and Cognitive Sciences

    • Cited by

    Topology Control in Self-managed Wireless Networks
    Nancy Alonistioti

    Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2010

    The vision for future telecommunication systems is considered as a representative example of a complex adaptive organization, where several elements, with various computational capabilities and network resources, are interconnected. The increased complexity and the continuously changing network environment make more intense the need for automation and for localized network management tasks. Self-management will allow the execution of advanced configuration actions, such as the change of the wireless network topology under various performance criteria. This paper focuses on the description of the principles and the architectural framework for the cognitive management of future communication systems, considering a complex radio access environment. This framework is used in order to present a solution on the autonomic topology control of future communication systems, where multi-hop links are established using the available relays stations, under the energy consumption constraint.

    View PDFchevron_right
    580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved