Filters








1,404 Hits in 10.6 sec

Towards a real-time interface between a biomimetic model of sensorimotor cortex and a robotic arm

Salvador Dura-Bernal, George L. Chadderdon, Samuel A. Neymotin, Joseph T. Francis, William W. Lytton
2014 Pattern Recognition Letters  
Brain-machine interfaces can greatly improve the performance of prosthetics.  ...  Utilizing biomimetic neuronal modeling in brain machine interfaces (BMI) offers the possibility of providing naturalistic motor-control algorithms for control of a robotic limb.  ...  used for 440 reinforcement learning in the brain model.  ... 
doi:10.1016/j.patrec.2013.05.019 pmid:26709323 pmcid:PMC4689209 fatcat:jzbqfte6xrfgxi5klyhruoatni

Evolutionary algorithm optimization of biological learning parameters in a biomimetic neuroprosthesis

S. Dura-Bernal, S. A. Neymotin, C. C. Kerr, S. Sivagnanam, A. Majumdar, J. T. Francis, W. W. Lytton
2017 IBM Journal of Research and Development  
Instead of adapting synaptic weights via machine learning, we employed major biological learning methods: spike-timing dependent plasticity and reinforcement learning.  ...  Embedding a biomimetic simulation in a closed-loop neuroprosthesis, which can read and write signals from the brain, will permit applications for amelioration of motor, psychiatric, and memory-related  ...  He then started researching brain-machine interfaces with John Chapin at SUNY Downstate, where he later obtained a faculty position.  ... 
doi:10.1147/jrd.2017.2656758 pmid:29200477 pmcid:PMC5708558 fatcat:t2wpsrowwfgghkconkn5di6gym

Measuring and modeling the motor system with machine learning [article]

Sébastien B. Hausmann and Alessandro Marin Vargas and Alexander Mathis and Mackenzie W. Mathis
2021 arXiv   pre-print
The utility of machine learning in understanding the motor system is promising a revolution in how to collect, measure, and analyze data.  ...  The field of movement science already elegantly incorporates theory and engineering principles to guide experimental work, and in this review we discuss the growing use of machine learning: from pose estimation  ...  Acknowledgments: The authors declare no conflicts of interest. We thank members of the Mathis Lab, Mathis Group and Travis DeWolf for comments.  ... 
arXiv:2103.11775v1 fatcat:rwdyr5gpszga7lutln3hmw2fqm

Measuring and modeling the motor system with machine learning

Sebastien B. Hausmann, Alessandro Marin Vargas, Alexander Mathis, Mackenzie W. Mathis
2021 Current Opinion in Neurobiology  
The utility of machine learning in understanding the motor system is promising a revolution in how to collect, measure, and analyze data.  ...  The field of movement science already elegantly incorporates theory and engineering principles to guide experimental work, and in this review we discuss the growing use of machine learning: from pose estimation  ...  Funding was provided, in part by the SNSF Grant #201057 to MWM.  ... 
doi:10.1016/j.conb.2021.04.004 pmid:34116423 fatcat:biacdnyth5dvrd7udappz6ylpy

Cortical Spiking Network Interfaced with Virtual Musculoskeletal Arm and Robotic Arm

Salvador Dura-Bernal, Xianlian Zhou, Samuel A. Neymotin, Andrzej Przekwas, Joseph T. Francis, William W. Lytton
2015 Frontiers in Neurorobotics  
Our techniques are applicable to the future development of brain neuroprosthetic control systems, and may enable enhanced brain-machine interfaces with the possibility for finer control of limb prosthetics  ...  The cortical model was trained using spike timing-dependent reinforcement learning to drive the virtual arm in a 2D reaching task.  ...  ACKNOWLEDGMENTS Research funded by DARPA grant N66001-10-C-2008 and NIH grant U01EB017695.  ... 
doi:10.3389/fnbot.2015.00013 pmid:26635598 pmcid:PMC4658435 fatcat:h672om5dtfeqxlsdpkbuqqkyki

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.  ...  Naturally, the human brain realizes these cognitive skills by prefrontal cortex which is a part of the neocortex. Previous studies about neurocognitive robotics would not meet these requirements.  ...  of different computational methods and machine learning paradigms.  ... 
doi:10.1109/access.2020.2998396 fatcat:p37fba6frbdbzkbrdepllwauwi

Towards an integration of deep learning and neuroscience [article]

Adam Marblestone, Greg Wayne, Konrad Kording
2016 arXiv   pre-print
Such a heterogeneously optimized system, enabled by a series of interacting cost functions, serves to make learning data-efficient and precisely targeted to the needs of the organism.  ...  In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively  ...  We thank Miles Brundage for an excellent Twitter feed of deep learning papers.  ... 
arXiv:1606.03813v1 fatcat:tmmholydqbcplbc5ihg76yip6e

Toward an Integration of Deep Learning and Neuroscience

Adam H. Marblestone, Greg Wayne, Konrad P. Kording
2016 Frontiers in Computational Neuroscience  
Such a heterogeneously optimized system, enabled by a series of interacting cost functions, serves to make learning data-efficient and precisely targeted to the needs of the organism.  ...  In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively  ...  These ideas are inspired by recent advances in machine learning, but we also propose that the brain has major differences from any of today's machine learning techniques.  ... 
doi:10.3389/fncom.2016.00094 pmid:27683554 pmcid:PMC5021692 fatcat:yikwc4h5yvfj7gwzlimtw5n6ai

Towards an integration of deep learning and neuroscience [article]

Adam Henry Marblestone, Greg Wayne, Konrad P Kording
2016 bioRxiv   pre-print
Such a heterogeneously optimized system, enabled by a series of interacting cost functions, serves to make learning data-efficient and precisely targeted to the needs of the organism.  ...  In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively  ...  These ideas are inspired by recent advances in machine learning, but we also propose that the brain has major differences from any of today's machine learning techniques.  ... 
doi:10.1101/058545 fatcat:4ryejpe2tnf7dgoaqhoastoiya

From 'Understanding the Brain by Creating the Brain' towards manipulative neuroscience

M. Kawato
2008 Philosophical Transactions of the Royal Society of London. Biological Sciences  
Ten years have passed since the Japanese 'Century of the Brain' was promoted, and its most notable objective, the unique 'creating the brain' approach, has led us to apply a humanoid robot as a neuroscience  ...  A theory of cerebellar internal models and a systems biology model of cerebellar synaptic plasticity is discussed.  ...  Brain-network interface is the term we have created for this project, and it is like a brain-machine interface or a brain-computer interface.  ... 
doi:10.1098/rstb.2008.2272 pmid:18375374 pmcid:PMC2610191 fatcat:ci6zc3nq7fdobhxw5win7d5ed4

A Symbiotic Brain-Machine Interface through Value-Based Decision Making

Babak Mahmoudi, Justin C. Sanchez, Josh Bongard
2011 PLoS ONE  
In the development of Brain Machine Interfaces (BMIs), there is a great need to enable users to interact with changing environments during the activities of daily life.  ...  We then implanted a dual micro-wire array in the primary motor cortex (M1) and the NAcc of rat brain and implemented a full closed-loop system in which robot actions were decoded from the single unit activity  ...  That action can be evaluated by the user to promote continuous learning. We call this framework a symbiotic brain-machine interface (S-BMI).  ... 
doi:10.1371/journal.pone.0014760 pmid:21423797 pmcid:PMC3056711 fatcat:t7onn6wmj5eedonsptkzl66o3y

SAL: an explicitly pluralistic cognitive architecture

David J. Jilk, Christian Lebiere, Randall C. O'Reilly, John R. Anderson
2008 Journal of experimental and theoretical artificial intelligence (Print)  
Similarly, Leabra incorporates three different learning mechanisms: small increments of Hebbian learning, a substantial component of error-driven learning, and in some cases reinforcement learning, which  ...  Machine learning algorithms, such as Bayesian approaches and reinforcement learning, characterise mathematically optimal solutions to problems.  ... 
doi:10.1080/09528130802319128 fatcat:rrpljyjqh5afvpwl2cw55ritci

Towards the neural population doctrine

Shreya Saxena, John P Cunningham
2019 Current Opinion in Neurobiology  
Together, these findings suggest an exciting trend towards a new era where neural populations are understood to be the essential unit of computation in many brain regions, a classic idea that has been  ...  We detail four areas of the field where the joint analysis of neural populations has significantly furthered our understanding of computation in the brain: correlated variability, decoding, neural dynamics  ...  Acknowledgements This work was supported by the Swiss National Science Foundation (Research Award P2SKP2_178197), NIH R01NS100066, Simons Foundation 542963, NSF NeuroNex DBI-1707398, The Gatsby Charitable  ... 
doi:10.1016/j.conb.2019.02.002 pmid:30877963 fatcat:6s2q32j3knfxvhdizloo6gojaa

Hierarchical motor control in mammals and machines

Josh Merel, Matthew Botvinick, Greg Wayne
2019 Nature Communications  
While motor neuroscience has recently focused on optimization of single, simple movements, AI has progressed to the generation of rich, diverse motor behaviors across multiple tasks, at humanoid scale.  ...  Less discussed in neuroscience are parallel advances in "synthetic motor control".  ...  Supplementary video examples of the NPMP architecture being reused are courtesy of Arun Ahuja and other co-authors associated with that research.  ... 
doi:10.1038/s41467-019-13239-6 pmid:31792198 pmcid:PMC6889345 fatcat:6r6qp2wbgbhibjnukzhjaosjny

Closed-Loop Brain–Machine–Body Interfaces for Noninvasive Rehabilitation of Movement Disorders

Frédéric D. Broccard, Tim Mullen, Yu Mike Chi, David Peterson, John R. Iversen, Mike Arnold, Kenneth Kreutz-Delgado, Tzyy-Ping Jung, Scott Makeig, Howard Poizner, Terrence Sejnowski, Gert Cauwenberghs
2014 Annals of Biomedical Engineering  
As a result, a more efficient and effective management of PD cardinal symptoms has emerged.  ...  Recently, the more invasive method of deep brain stimulation (DBS) showed significant improvement of the physical symptoms associated with these disorders.  ...  A system framework towards neurofeedback noninvasive rehabilitation of movement disorders by means of closed-loop brain-machine-body interfaces.  ... 
doi:10.1007/s10439-014-1032-6 pmid:24833254 pmcid:PMC4099421 fatcat:4jbihnphwbelhhamj7a7svrnmm
« Previous Showing results 1 — 15 out of 1,404 results