Learning Intelligent Distribution Agent: Fundamentals and Applications

By Fouad Sabry

What Is Learning Intelligent Distribution Agent

The LIDA cognitive architecture is an integrated artificial cognitive system that seeks to simulate a broad spectrum of cognition found in biological systems, ranging from low-level perception/action to high-level reasoning. It does this by using a combination of natural and artificial cognitive processes. The LIDA architecture is experimentally anchored in cognitive science and cognitive neuroscience, and was developed principally by Stan Franklin and colleagues at the University of Memphis. In addition to generating hypotheses that can direct subsequent research, the architecture can also provide support for control structures that can be used by software agents and robots. The LIDA conceptual model is not only meant to be used as a tool for the purpose of thinking about how brains operate, but it also provides credible explanations for a large number of cognitive processes.

How You Will Benefit

(I) Insights, and validations about the following topics:

Chapter 1: LIDA (cognitive architecture)

Chapter 2: List of artificial intelligence projects

Chapter 3: Cognitive science

Chapter 4: Artificial consciousness

Chapter 5: Cognitive model

Chapter 6: Soar (cognitive architecture)

Chapter 7: Stan Franklin

Chapter 8: Global workspace theory

Chapter 9: Cognitive architecture

Chapter 10: Computational theory of mind

(II) Answering the public top questions about learning intelligent distribution agent.

(III) Real world examples for the usage of learning intelligent distribution agent in many fields.

(IV) 17 appendices to explain, briefly, 266 emerging technologies in each industry to have 360-degree full understanding of learning intelligent distribution agent' technologies.

Who This Book Is For

Professionals, undergraduate and graduate students, enthusiasts, hobbyists, and those who want to go beyond basic knowledge or information for any kind of learning intelligent distribution agent.

• Language: English
• Publisher: One Billion Knowledgeable
• Release date: Jun 23, 2023

Book preview

Chapter 1: LIDA (cognitive architecture)

An integrated artificial cognitive system called LIDA (Learning Intelligent Distribution Agent) seeks to replicate a wide range of biological systems' cognition, from basic perception and action to complex reasoning. The LIDA architecture, which was largely created by Stan Franklin and colleagues at the University of Memphis, is empirically supported by cognitive science and cognitive neuroscience. The design can enable control frameworks for software agents and robots, as well as offering hypotheses to direct further research. The LIDA conceptual model is meant to be a tool for thinking about how brains function, offering reasonable explanations for various cognitive processes.

The LIDA architecture and its associated conceptual model are based on two hypotheses: 1) A significant portion of human cognition relies on interactions between conscious contents, multiple memory systems, and action selection that are often iterated (10 Hz), known as cognitive cycles. 2) These cognitive cycles act as the atoms of cognition, the building blocks of higher-order cognitive processes.

LIDA is a hybrid architecture because it uses a range of computational processes that were chosen for their psychological validity, despite neither being strictly symbolic nor connectionist. These mechanisms are used by the modules and processes that make up the LIDA cognitive cycle.

Several modules used in the LIDA architecture were created utilizing computational methods from the new AI. Variations of the Copycat Architecture are among them, The LIDA architecture aims to model a significant component of human cognition as a complete, conceptual, and computational cognitive architecture.

The comprehension phase, the attention (awareness) phase, and the action selection and learning phase can all be considered subphases of the LIDA cognitive cycle. Incoming inputs trigger low-level feature detectors in sensory memory to start the comprehension process. Higher-level feature detectors feed in to more abstract entities like objects, categories, actions, events, etc. in the output, which engages perceptual associative memory. The resulting percept travels to the workspace where it prompts both Declarative Memory and Transient Episodic Memory, resulting in local associations. A current situational model, which represents the agent's perception of the current circumstance, is created when these local connections are coupled with the percept. The formation of coalitions of the most prominent elements of the present situational model marks the start of the attention phase. These coalitions then compete for attention, or a position in the current conscious contents. The learning and action selection phases are then launched by the subsequent global broadcast of these conscious contents. As the conscious broadcast reaches the several types of memory, perceptual, episodic, and procedural, new entities and connections are formed, and existing ones are reinforced. Possible action schemes are instantiated from procedural memory and transmitted to action selection in synchrony with all of this learning, using the conscious contents, where they compete to be the behavior chosen for this cognitive cycle. The chosen behavior prompts the production of an appropriate algorithm for its execution in sensory-motor memory, completing the cognitive cycle.

Known as V-Mattie, Virtual Mattie is a software agent. Many of the computational techniques discussed above were used by V-Mattie.

Conscious Mattie was created as a result of V-transition Mattie's into the Global Workspace Theory (GWT) by Baars, a software agent with the same domain and tasks whose architecture included a consciousness mechanism à la GWT.

Mattie conscious was the first operationally, albeit not remarkably, aware software agent.

IDA was created by conscious Mattie.

The US Navy created the IDA (Intelligent Distribution Agent) to carry out the duties of the so-called detailers in human resources. Each sailor is given a new billet at the conclusion of their term of duty. Distributive assignment is the name given to this process. To carry out these new missions, the Navy has roughly 300 full-time detailers on staff. By automating the function of the detailer, IDA's job is to make this procedure easier. Former detailers evaluated IDA, which the Navy approved. Around $1,500,000 was donated to the IDA project by various Navy entities.

A number of learning styles and modes were initially added to the IDA design to create the LIDA (Learning IDA) architecture, Hobstadter, D. (1995). Computer models of the basic thought processes: Flexible Concepts and Ingenious Analogies. Basic Books in New York.

Marshal, J. (2002). A self-monitoring cognitive architecture for analogy-making is called Metacat. Proceedings of the 24th Annual Conference of the Cognitive Science Society, edited by W. D. Gray and C. D. Schunn, pp. 631-636. Lawrence Erlbaum Associates, Mahwah, NJ

P. Kanerva (1988). Distributed Memory in Sparse. The MIT Press, Cambridge, MA

Fuentes, O.; Rao, R. P. N. (1998). Predictive Sparse Distributed Memory for Hierarchical Learning of Navigational Behaviors in an Autonomous Robot, 2017-08-10 at the Wayback Machine. 31, 87–113, Machine Learning

Drescher, George L. (1991). Constructivist Approach to Artificial Intelligence: Made-up Minds

The authors are Chaput, H. H., Kuipers, and Miikkulainen (2003). Constructivist Learning: The Schema Mechanism in Neural Form. Paper presented at the Kitakyushu, Japan's Proceedings of WSOM '03: Workshop on Self-Organizing Maps

How to do the right thing: Maes, P. 1989. Connection Science 1:291-323

Tyrell, T. (1994). An assessment of Maes's bottom-up behavior selection mechanism. 307–348 in Adaptive Behavior, 2.

Intelligence without Representation by R.A. Brooks. Elsevier, Artificial Intelligence, 1991

Patterson, F. G. J., and Franklin, S. (2006). The LIDA Architecture: Improving an Intelligent, Autonomous Software Agent with New Learning Methods Integrated Design and Process Technology 2006 Proceedings: Society for Design and Process Science

Franklin S, Ramamurthy U, D'Mello S, McCauley L, Negatu A, Silva R, and Datla V. (2007). LIDA: A computerized representation of the global workspace theory and learning progress. The theoretical underpinnings and modern methods at the AAAI Fall Symposium on AI and Consciousness. AAAI, Arlington, VA

Bars, B. J. (1988). a consciousness-related cognitive theory. Harvard University Press, Cambridge

Varela, F. J., Thompson, and Rosch each contributed one (1991). The Body-Mind. Massachusetts's Cambridge: MIT Press

1999. Barsalou, L. W. systems of perceptual symbols. 22:577–609, Behavioral and Brain Sciences. The MIT Press, MA

Hitch, G. J.; Baddeley, A. D. (1974). a working memory. In The Psychology of Learning and Motivation, edited by G. A. Bower (pp. 47–89). Academic Press, New York

A. M. Glenberg 1997. Why we have memories. Cognitive and Behavioral Sciences 20:1–19

Long-term working memory was studied by K. A. Ericsson and W. Kintsch in 1995. Psychological Review 102:21-245

1999. Sloman, A. What Kind of Architecture is Needed for an Agent with Human-like Qualities? Foundations of Rational Agency, ed. M. Wooldridge and A. Rao, Kluwer Academic Publishers, Dordrecht, Netherlands

Franklin, S., and A. Graesser, 1997. A Taxonomy for Autonomous Agents: Is it an Agent or Just a Program? Intelligent Agents III: Proceedings of the Third International Workshop on Agent Theories, Architectures, and Languages, Springer-Verlag, 1997, pp. 21–35

The authors are Franklin, S., Graesser, A., Olde, B., Song, H., and Negatu (1996, Nov). An intelligent clerical agent, Virtual Mattie. A paper was presented at the Embodied Cognition and Action Symposium at the AAAI in Cambridge, Massachusetts.

McCauley, L., Kelemen, A., & Franklin, S. (1998). IDA: An Intelligent Data Architecture IEEE Conf on Systems, Man, and Cybernetics: IEEE Press, pp. 2646-2651

Benjamin S. (2003). A Conscious Artifact: Is IDA? 10, 47–66 of the Journal of Consciousness Studies

McCauley, L., & Franklin, S. (2003). communication with IDA. Agent Autonomy, edited by H. Hexmoor, C. Castelfranchi, and R. Falcone (pp. 159–186). Kluwer, Dordrecht

Sidney K. D'Mello, U. Ramamurthy, A. Negatu, and S. Franklin (2006). A Mechanism for Procedural Learning to Acquire Novel Skills. 184–185 in T. Kovacs and James A. R. Marshall (Eds. ), Proceedings of Adaptation in Artificial and Biological Systems, AISB'06 (Vol. Society for the Study of Artificial Intelligence and the Simulation of Behavior, Bristol, England

(2005, March 21–23). Franklin, S. Recognizing, categorizing, and relating: Perceptual Memory and Learning. The American Association for Artificial Intelligence (AAAI), Stanford University, Palo Alto, California, presented a paper at the Symposium on Developmental Robotics.

Patterson, F. G. J., and Franklin, S. (2006). The LIDA Architecture: