Filters








9 Hits in 7.2 sec

A Multi-cellular Developmental Representation for Evolution of Adaptive Spiking Neural Microcircuits in an FPGA

Hooman Shayani, Peter J. Bentley, Andy M. Tyrrell
2009 2009 NASA/ESA Conference on Adaptive Hardware and Systems  
Here, a bio-inspired developmental genotype-phenotype mapping for evolution of spiking neural microcircuits in an FPGA is introduced, based on a digital neuron model and cortex structure suggested and  ...  Suitability of the representation for evolution of useful architectures and its adaptability is shown through statistical analysis and examples of scalability, modularity and fault-tolerance.  ...  Following a nature-inspired approach, here we propose a bio-plausible developmental genotype-phenotype mapping for evolution of spiking neural microcircuits in an FPGA.  ... 
doi:10.1109/ahs.2009.39 dblp:conf/ahs/ShayaniBT09 fatcat:hy7bw7i6avevjjadkwtpyamgba

Plasticity and Adaptation in Neuromorphic Biohybrid Systems

Richard George, Michela Chiappalone, Michele Giugliano, Timothée Levi, Stefano Vassanelli, Johannes Partzsch, Christian Mayr
2020 iScience  
The recent years have seen both advances in the theoretical aspects of spiking neural networks for their use in classification and control tasks and a progress in electrophysiological methods that is pushing  ...  At the forefront of these new technologies, artificial and biological neural networks are tightly coupled, offering a novel "biohybrid" experimental framework for engineers and neurophysiologists.  ...  ., and C.M.) and project ''IN-FET'' (GA n. 862882 to M.G.).  ... 
doi:10.1016/j.isci.2020.101589 pmid:33083749 pmcid:PMC7554028 fatcat:a7iwoyllezdwbor5chqfym45pq

Towards an integration of deep learning and neuroscience [article]

Adam Marblestone, Greg Wayne, Konrad Kording
2016 arXiv   pre-print
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  ...  Here we think about the brain in terms of these ideas.  ...  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  
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  ...  In support of these hypotheses, we argue that a range of implementations of credit assignment through multiple layers of neurons are compatible with our current knowledge of neural circuitry, and that  ...  ACKNOWLEDGMENTS We thank Ken Hayworth for key discussions that led to this paper. We thank Ed Boyden, Chris Eliasmith, Gary  ... 
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
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  ...  Here we think about the brain in terms of these ideas.  ...  Acknowledgments We thank Ken Hayworth for key discussions that led to this paper.  ... 
doi:10.1101/058545 fatcat:4ryejpe2tnf7dgoaqhoastoiya

A world survey of artificial brain projects, Part I: Large-scale brain simulations

Hugo de Garis, Chen Shuo, Ben Goertzel, Lian Ruiting
2010 Neurocomputing  
As well as reviewing the particulars of these simulation projects, we position them in a broader perspective, comparing at the different underlying definitions of the concept of "simulation," noting that  ...  This article constitutes the first half of a two-part world survey of artificial brain projects: this part dealing with large-scale brain simulations, and the second part with biologically inspired cognitive  ...  In the year 2000, Edelman's team developed a BBD called NOMAD (an acronym for Neurally Organized Mobile Adaptive Device) which contained many sensors, for example, (a) a panning tilting color camera used  ... 
doi:10.1016/j.neucom.2010.08.004 fatcat:hfjpyo3mw5c65bljetgtcdhy7y

ABSTRACTS OF PAPERS AT THE SEVENTY-FIRST ANNUAL MEETING OF THE SOCIETY OF GENERAL PHYSIOLOGISTS: The Optical Revolution in Physiology: From Membrane to Brain

2017 The Journal of General Physiology  
Ca 2+ transients in ICC-DMP activate inward currents that can regulate the excitability of the small intestine provides a signaling mechanism responsible for transduction of enteric neuronal input. 3.  ...  Aim: Measure Ca 2+ transients in ICC-DMP in situ that are elicited or suppressed by excitatory and inhibitory motor neural inputs.  ...  a comprehensive toolkit for optogenetic interrogation of neural inhibition.  ... 
doi:10.1085/jgp.149.9.889 fatcat:nplsscsocfcpdntcc7wfv6pn4i

Structural plasticity in neuromorphic systems

Richard Miru George
2018
This allows the implementation of spiking neural networks for the processing of biosignals in hardware.  ...  Early experiments on conventional hardware formed the basis for a 141 more extensive application in spiking neural networks.  ...  Algorithm 9: Network operation procedure. synapse.W denotes the object attribute W of the object synapse Data: BRIAN connection object synapses Result: BRIAN connection object synapses 1 W ← synapses.W  ... 
doi:10.5167/uzh-153150 fatcat:4mwsp4qge5bshbg3j4ffep4ake

VLSI Implementation of a Spiking Neural Network

Andreas Grübl
2007
The work is based upon an analog VLSI model of a spiking neural network featuring an implementation of spike timing dependent plasticity (STDP) locally in each synapse.  ...  VLSI Implementation of a Spiking Neural Network Within the scope of this thesis concepts and dedicated hardware have been developed that allow for building large scale hardware spiking neural networks.  ...  The content in the case of a multi-chip spiking neural network could be configuration data for the analog parameters or the synapse configuration data for the network chip.  ... 
doi:10.11588/heidok.00007457 fatcat:qqckyygwqjc5zkb5baetjktas4