33,197 Hits in 4.0 sec

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning [article]

Mingde Zhao, Zhen Liu, Sitao Luan, Shuyuan Zhang, Doina Precup, Yoshua Bengio
2021 arXiv   pre-print
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning.  ...  The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to be small.  ...  well as about the writing of the introduction section), Min Lin (about the design of the dynamics model as well as the early stage brainstorming) and Ian Porada (for consistently supporting the student  ... 
arXiv:2106.02097v3 fatcat:e3deycfd6zbvnprwzj5dotwige

A computational model of attentional learning in a cognitive agent

Usef Faghihi, Ryan McCall, Stan Franklin
2012 Biologically Inspired Cognitive Architectures  
In this paper, we describe conceptual and computational model of attention and attentional learning for intelligent software agents in the context of the broad-based biologically inspired cognitive architecture  ...  A basic implementation of such an attentional learning mechanism in a LIDA-based agent is presented.  ...  ACKNOWLEDGMENT We would like to thank the FQRNT for its financial support and all the members of CCRG lab who have contributed to the development of the LIDA's computational model.  ... 
doi:10.1016/j.bica.2012.07.003 fatcat:ixthr4z2trfphecyk6urkf3f5y

Artificial Motivation for Cognitive Software Agents

Ryan J. McCall, Stan Franklin, Usef Faghihi, Javier Snaider, Sean Kugele
2020 Journal of Artificial General Intelligence  
Natural selection has imbued biological agents with motivations moving them to act for survival and reproduction, as well as to learn so as to support both.  ...  Here we present a biologically inspired motivation system, based on feelings (including emotions) integrated within the LIDA cognitive architecture at a fundamental level.  ...  learning, and model-free and model-based learning.  ... 
doi:10.2478/jagi-2020-0002 fatcat:szpacc3cyzcwximrx7ubqcodo4

Planning with Brain-inspired AI [article]

Naoya Arakawa
2020 arXiv   pre-print
It aims to present existing planning models as references for realizing the planning function in brain-inspired AI or artificial general intelligence (AGI).  ...  This article surveys engineering and neuroscientific models of planning as a cognitive function, which is regarded as a typical function of fluid intelligence in the discussion of general intelligence.  ...  Model-based reinforcement learning uses a model for estimating the environment. In particular, an RL system that uses a model at the time of action can perform planning as defined in this article.  ... 
arXiv:2003.12353v1 fatcat:rpevcadswjgldjk4jvfygbzkru

Global Workspace Theory, its LIDA model and the underlying neuroscience

Stan Franklin, Steve Strain, Javier Snaider, Ryan McCall, Usef Faghihi
2012 Biologically Inspired Cognitive Architectures  
A biologically inspired cognitive architecture must draw its insights from what is known from animal (including human) cognition.  ...  Here we argue that the LIDA architecture's breadth, flexible motivations using feelings, explicit attention mechanism, and continual, incremental and online learning in several modalities provide a significant  ...  A LIDA--based agent attends to what is currently most salient based on its situational awareness; 12) Can reinforcement learning and motivation modulate perceptual and cognitive decision--making?  ... 
doi:10.1016/j.bica.2012.04.001 fatcat:jopew7bvlvehflux4cjc72uyxm


2012 International Journal of Machine Consciousness  
The main motivation for this work is to investigate the advantages given by machine consciousness, while in the control of software agents.  ...  A completely codelet-based system "Core" has been implemented, serving the whole architecture. * Preprint  ...  Acknowledgments We would like to thank CNPq (Conselho Nacional de Desenvolvimento Científico e Tecnológico) and CAPES (Coordenação de Aperfeiçoamento de Pessoal de Nível Superior) for the financial support  ... 
doi:10.1142/s1793843012400197 fatcat:mn3sse4prvgjblkgi35bvbrugy

MIRA: A Computational Neuro-Based Cognitive Architecture Applied to Movie Recommender Systems [article]

Mariana B. Santos, Amanda M. Lima, Lucas A. Silva, Felipe S. Vargas, Guilherme A. Wachs-Lopes, Paulo S. Rodrigues
2019 arXiv   pre-print
of LIDA as a path to be followed for the study and generation of computational agents inspired by neural behaviors.  ...  Considering that the proposed model achieved a similar behavior to the traditional models under conditions expected to be similar for natural systems, it can be said that MIRA reinforces the applicability  ...  of High Level Graduation, Brazil) and FEI (Foundation for Ignatian Education, São Paulo, Brazil) for any direct or indirect support they have given to this research project.  ... 
arXiv:1902.09291v2 fatcat:of64xmpy45erzph6gbadnbhhoq

Computational Aspects of Cognition and Consciousness in Intelligent Devices

Robert Kozma, Hrand Aghazarian, Terry Huntsberger, Eddie Tunstel, Walter Freeman
2007 IEEE Computational Intelligence Magazine  
Continuous adaptation and learning is a key component of computationally intelligent devices, which is achieved using dynamic models of cognition and consciousness.  ...  , more faithful, Biologically-inspired architectures are widely used for control of mobile robots and demonstrating robust navigation capabilities in challenging real life scenarios.  ...  KIV is a biologically based cognitive brain model capable of learning and responding to environmental inputs robustly and creatively, based on its experience.  ... 
doi:10.1109/mci.2007.385369 fatcat:jnvmwtgnrfcjnclzqaocot54ry

A Biopsychically Inspired Cognitive System for Intelligent Agents in Aerospace Applications

Xudan Xu, James Graham, Fnu Basawaraj, J. Zhu, Janusz Starzyk, Ping Zhang
2012 Infotech@Aerospace 2012  
A biopsychically inspired cognitive system is proposed based on the biological Central Nervous System architecture.  ...  The proposed cognitive system can be used for intelligent agents for autonomous scientific exploration, as well as in agriculture, rescue and military applications or as a basis for cooperative groups.  ...  Jeff Vancouver a professor of Psychology at Ohio University for insightful discussions.  ... 
doi:10.2514/6.2012-2412 dblp:conf/itaero/XuGBZSZ12 fatcat:72k5y6xhw5g6hgksrhmdjbiei4

Computational Modeling of Prefrontal Cortex for Meta-Cognition of a Humanoid Robot

Evren Daglarli
2020 IEEE Access  
A reinforcement meta-learning based explainable artificial intelligence (xAI) procedure is applied to the working memory regions of the computational prefrontal cortex model.  ...  In this study, we present a novel solution that covers a computational model of the prefrontal cortex for humanoid robots.  ...  [42] struggled on imitating self-consciousness using brain-inspired modeling for a humanoid robot.  ... 
doi:10.1109/access.2020.2998396 fatcat:p37fba6frbdbzkbrdepllwauwi

Natural Morphological Computation as Foundation of Learning to Learn in Humans, Other Living Organisms, and Intelligent Machines

Gordana Dodig-Crnkovic
2020 Philosophies  
As all natural systems possessing intelligence are cognitive systems, we describe the evolutionary arguments for the necessity of learning to learn for a system to reach human-level intelligence through  ...  The question is, what at this stage of the development the inspiration from nature, specifically its computational models such as info-computation through morphological computing, can contribute to machine  ...  Acknowledgments: The author would like to thank anonymous reviewers for very helpful, constructive, and instructive review comments.  ... 
doi:10.3390/philosophies5030017 fatcat:6svndrki2nazbfbo5ayubctwsa

The LIDA Model as a Foundational Architecture for AGI [chapter]

Usef Faghihi, Stan Franklin
2012 Atlantis Thinking Machines  
A LIDA-based agent attends to what is most salient based on its situational awareness; 12) Can reinforcement learning and motivation modulate perceptual and cognitive decisionmaking? Yes; ).  ...  Episodic learning in the LIDA model is also a matter of generate and test, with such learn- coalition is added to the Global Workspace to compete for consciousness.  ... 
doi:10.2991/978-94-91216-62-6_7 fatcat:gbqh3sbndfblliqb57fbr7skxe

Implementation of Emotional Learning for Cognitive Tutoring Agents

Usef Faghihi, Pierre Poirier, Daniel Dubois, Mohamed Gaha, Roger Nkambou
2008 2008 Seventh Mexican International Conference on Artificial Intelligence  
The model replicates the amygdala's emotional influence over different parts of the system as a means of preparing the system for action, biasing action selection and improving the agent's self-resilience  ...  In this paper we describe the reproduction of emotional mechanisms in the cognitive agent CTS (Conscious Tutoring System).  ...  Based on Hofstadter et al.'s idea, a codelet is a very simple agent, "a small piece of code that is specialized for some comparatively simple task".  ... 
doi:10.1109/micai.2008.45 fatcat:kj42bleyjzddnosnlukk2v7ic4

A New Vision About AI and Situation Awareness Model of Auto-driving with Implicit Memory

Hang SONG, Bo-han JIANG, Da-xue LIU
2018 DEStech Transactions on Computer Science and Engineering  
This paper is enlightenment by implicit memory, situation awareness model of Ensley's and the way a very young child watching, touching and knowing the objects of the world.  ...  As to car-driving, an action-taking model based on situation awareness is presented, which shows two main action-taking ways. One is Reaction Chain; the other is Implicit/Action Ring.  ...  Reinforcement learning (RL) 6 is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment.  ... 
doi:10.12783/dtcse/cnai2018/24168 fatcat:jtxrbgsuw5cptafbkrnpehlswa

Metacognition for a Common Model of Cognition

Jerald D. Kralik, Jee Hang Lee, Paul S. Rosenbloom, Philip C. Jackson, Susan L. Epstein, Oscar J. Romero, Ricardo Sanz, Othalia Larue, Hedda R. Schmidtke, Sang Wan Lee, Keith McGreggor
2018 Procedia Computer Science  
This paper provides a starting point for the development of metacognition in a common model of cognition.  ...  Finally, we identify pressing design issues for the future.  ...  Examples from cognitive neuroscience and cognitive science provide a clearer view of Category 1 metacognition. Arbitration of Model-Free vs Model-Based Reinforcement Learning.  ... 
doi:10.1016/j.procs.2018.11.046 fatcat:zgtkd3icevdffaet6pvnjdrduu
« Previous Showing results 1 — 15 out of 33,197 results