Filters








1,833 Hits in 3.7 sec

Modularity and Specialized Learning: Mapping between Agent Architectures and Brain Organization [chapter]

Joanna Bryson, Lynn Andrea Stein
2001 Lecture Notes in Computer Science  
The design of complete autonomous agents (CAA), such as mobile robots or virtual reality characters, has been dominated by modular architectures and context-driven action selection and learning.  ...  In particular, we are interested in examining the biological phenomena of modularity and specialized learning.  ...  Around 1986 a new paradigm based on greater modularity became established in mobile robotics [40] . This paradigm, behavior-based AI (BBAI), favored niche-specific solutions for CAA.  ... 
doi:10.1007/3-540-44597-8_7 fatcat:lllyh5qgpzcsln2gs2f7azwdda

Breaking the silence: Brain?computer interfaces (BCI) for communication and motor control

Niels Birbaumer
2006 Psychophysiology  
Invasive multielectrode BCIs in otherwise healthy animals allowed execution of reaching, grasping, and force variations based on spike patterns and extracellular field potentials.  ...  At present no firm conclusion about the clinical utility of BCI for the control of voluntary movement can be made.  ...  Strong and anatomically specific effects of self-induced cortical changes on behavior and cognition; 2.  ... 
doi:10.1111/j.1469-8986.2006.00456.x pmid:17076808 fatcat:pswbdum2rrdqhdljd2j2bvesoi

On developmental mental architectures

Juyang Weng
2007 Neurocomputing  
Experiments are discussed with emphasis on their architectures. r 2007 Published by Elsevier B.V.  ...  If an agent runs a learning algorithm (e.g., the Q-learning algorithm) but it does not sense the voluntary decision process using the sensors that are linked to its entry point for sensors, the agent is  ...  Supervised and reinforcement learning, based on the Markov decision Process (MDP) architecture (single-or multi-level), enables a robot (an embodied agent) to learn autonomously while the environment (  ... 
doi:10.1016/j.neucom.2006.07.017 fatcat:pn6xs6gp5nfmjj4ft6hobakiea

A bio-inspired solution for a local autonomous, reflex, obstacle avoiding behavior

Dobrea Monica-Claudia, Dobrea Dan Marius
2011 ISSCS 2011 - International Symposium on Signals, Circuits and Systems  
The solution we proposed for a robot with 36 evenly distributed infrared (IR) sensors is a very simple one, based only on a minimal artificial neural network (ANN) trained with a backpropagation-like algorithm  ...  Computationally cheap, the online learning algorithm we implemented proved to be very successful in both, static and dynamic clustered environment.  ...  A behavior controller based on a minimal multilayer perceptron network and trained with a new introduced biological-like backpropagation (BBP) algorithm was considered in order to meet the online and in  ... 
doi:10.1109/isscs.2011.5978688 fatcat:ziagr4bygvfwrgrmtuipy7lhvq

Brain Human Interfaces

Gabriela ENE, Maria STANCIU
2017 Economy Informatics  
We also analyze the impact and usefulness of such system in an economic environment, where the choices and decisions are made based on thoughts, comparisons, data series, data reports and many other factors  ...  Brain Computer Interfaces require cross science learning and research, like computer programming, psychology, biology, design, and data mining.  ...  These systems should work on a game theory approach, where each agent will rationally react to the behavior of other agents, so that joint decisions achieve a balance, similar to a standard economic system  ... 
doaj:72f2dd4ebc7d442aa53543de8eb00812 fatcat:z6yngcg4izftpj4unlzbh5zoem

What is the role of brain mechanisms underlying arousal in recovery of motor function after structural brain injuries?

Andrew M. Goldfine, Nicholas D. Schiff
2011 Current Opinion in Neurology  
Purpose of review Standard neurorehabilitation approaches have limited impact on motor recovery in patients with severe brain injuries.  ...  Recent findings Animal and human neuroimaging studies are elucidating the neuroanatomical bases of arousal and of arousal regulation, the process by which the cerebrum mobilizes resources.  ...  Machine-learning algorithms allow for detection of more complex behaviors such as reaching and grasping [81 ] .  ... 
doi:10.1097/wco.0b013e32834cd4f5 pmid:22002078 pmcid:PMC3675222 fatcat:rpfmc2a33bgpjdz2tu6j4kmwae

Cellular Resolution Functional Imaging in Behaving Rats Using Voluntary Head Restraint

Benjamin B. Scott, Carlos D. Brody, David W. Tank
2013 Neuron  
Here we describe an integrated two-photon microscope and behavioral apparatus that allows cellular resolution functional imaging of cortical regions during epochs of voluntary head restraint.  ...  High-throughput operant conditioning systems for rodents provide efficient training on sophisticated behavioral tasks.  ...  On each session, a field of view was selected in layer II/III (150-300 mm below the cortical surface) based on the presence of large numbers of labeled cells.  ... 
doi:10.1016/j.neuron.2013.08.002 pmid:24055015 pmcid:PMC4068252 fatcat:4ezkdiejcvgxxmjv2l2hfm62eq

A stochastic policy search model for matching behavior

ZhenBo Cheng, Yu Zhang, ZhiDong Deng
2011 Science China Information Sciences  
Based on this model, an algorithm that satisfies the matching law is derived under some simple assumptions.  ...  In addition, the matching behaviors in two classical experiments are reproduced using the algorithm.  ...  The authors would like to thank Yao Wentao and Yang Bo for their helpful discussions on this work.  ... 
doi:10.1007/s11432-011-4304-x fatcat:dt75emwtcncpnapubda2clsnl4

Brain-controlled robots

Mitsuo Kawato
2008 2008 IEEE International Conference on Robotics and Automation  
the monkey's voluntary locomotion and influenced its brain activity.  ...  CB-i's locomotion-like movement was video-recorded and projected on a screen in front of the monkey.  ...  Recent computational studies on how the brain generates behaviors are progressing rapidly.  ... 
doi:10.1109/robot.2008.4543175 dblp:conf/icra/Kawato08 fatcat:kmoisj4vfbeghlu6ghbhfxejlq

Brain controlled robots

Mitsuo Kawato
2008 HFSP Journal  
the monkey's voluntary locomotion and influenced its brain activity.  ...  CB-i's locomotion-like movement was video-recorded and projected on a screen in front of the monkey.  ...  Recent computational studies on how the brain generates behaviors are progressing rapidly.  ... 
doi:10.2976/1.2931144 pmid:19404467 pmcid:PMC2645562 fatcat:wm33yqzw4beapgfk72sucuxn5q

Computational Models of Cognitive and Motor Control [chapter]

Ali A. Minai
2015 Springer Handbook of Computational Intelligence  
However, over the last three decades, attention has turned increasingly towards "higher" functions related to cognition, decision-making and voluntary behavior.  ...  supervised learning (Kawato and Gomi, 1992) , and the basal ganglia provide the mechanisms for selecting among actions and learning appropriate ones through reinforcement learning (Graybiel, 1995 (Graybiel  ...  Learning in the model is based on a variant of the EM algorithm.  ... 
doi:10.1007/978-3-662-43505-2_35 fatcat:xbkf3dhiuzbdnfgxlcpkairbme

The Reward Signal of Midbrain Dopamine Neurons

Wolfram Schultz
1999 Physiology  
They are based on behavioral learning theories that assume that learning depends crucially on the discrepancy or error between the prediction of reinforcement and its actual occurrence (1, 8) .  ...  Models using temporal difference algorithms learn a wide variety of behavioral tasks, reaching from balancing a pole on a cart wheel to playing world-class backgammon (for references, see Ref. 11).  ... 
doi:10.1152/physiologyonline.1999.14.6.249 pmid:11390860 fatcat:e7sebne2cvax7jbdvpuxt3rpni

Editorial: The Embodied Brain: Computational Mechanisms of Integrated Sensorimotor Interactions With a Dynamic Environment

Mario Senden, Judith Peters, Florian Röhrbein, Gustavo Deco, Rainer Goebel
2020 Frontiers in Computational Neuroscience  
important scientific insights into embodied sensorimotor systems while another four contributions present comprehensive frameworks and toolchains that support the interdisciplinary study of embodied agents  ...  Editorial on the Research Topic The Embodied Brain: Computational Mechanisms of Integrated Sensorimotor Interactions With a Dynamic Environment The paradigm shift toward an action-oriented view (Engel  ...  AUTHOR CONTRIBUTIONS All authors acted as guest editors on the Research Topic. MS and JP wrote the Editorial.  ... 
doi:10.3389/fncom.2020.00053 pmid:32625074 pmcid:PMC7314992 fatcat:o4j7tehc5zaejlgrfmeye2tg4i

Average-Payoff Reinforcement Learning [chapter]

2017 Encyclopedia of Machine Learning and Data Mining  
ARTDP is based on Dynamic Programming (DP), but unlike conventional DP, which consists of off-line algorithms, ARTDP is an on-line algorithm because it uses agent behavior to guide its computation.  ...  Agent-Based Computational Models Artificial Societies Agent-Based Modeling and Simulation Artificial Societies Agent-Based Simulation Models Artificial Societies AIS Artificial Immune Systems Algorithm  ...  Cross-References Efficient Exploration in Reinforcement Learning Hierarchical Reinforcement Learning Model-Based Reinforcement Learning  ... 
doi:10.1007/978-1-4899-7687-1_100029 fatcat:jub4ulyg45abnf4qgutimczie4

A/B Testing [chapter]

2017 Encyclopedia of Machine Learning and Data Mining  
ARTDP is based on Dynamic Programming (DP), but unlike conventional DP, which consists of off-line algorithms, ARTDP is an on-line algorithm because it uses agent behavior to guide its computation.  ...  Agent-Based Computational Models Artificial Societies Agent-Based Modeling and Simulation Artificial Societies Agent-Based Simulation Models Artificial Societies AIS Artificial Immune Systems Algorithm  ...  Cross-References Efficient Exploration in Reinforcement Learning Hierarchical Reinforcement Learning Model-Based Reinforcement Learning  ... 
doi:10.1007/978-1-4899-7687-1_100507 fatcat:bg6sszljsrax5heho4glbcbicu
« Previous Showing results 1 — 15 out of 1,833 results