The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
Filters
Continuous or discrete attractors in neural circuits? A self-organized switch at maximal entropy
[article]
2007
arXiv
pre-print
Preserved Fulltext
Other Versions
In recurrent neural network models, continuous and discrete attractors are separately modeled by distinct forms of synaptic prescriptions (learning rules). ...
In that case, there is no processing of sensory information and neural activity displays maximal entropy. ...
The solutions of this equation are the attractors of the recurrent neural dynamics, in absence of the stimulus. ...
arXiv:0707.3511v2
fatcat:gl22fb4yxzd47abovmb7sfbcha
Artificial Neural Networks
[chapter]
2013
Springer Series in Bio-/Neuroinformatics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Klaassen Attractor Learning of Recurrent Neural Networks 371 K. Gouhara, H. Takase, Y. Uchikawa, K. ...
Priigel-Bennet Ockham's Nets: Self-Adaptive Minimal Neural Networks 183 GD. Kendall, TJ.Hall The Generalisation Ability of Dilute Attractor Neural Networks 187 C. ...
Self-organizing Neural Network Apllication to Technical Process Parameters Estimation 579 E. Govekar, E. Susie, P. Muzic, I. Grabec High-precision Robot Control: The Nested Network 583 A. ...
doi:10.1007/978-3-319-00861-5_4
fatcat:l3v3etbv6zfxlcfkxnzml4v3xu
Spatiotemporal Computations of an Excitable and Plastic Brain: Neuronal Plasticity Leads to Noise-Robust and Noise-Constructive Computations
2014
PLoS Computational Biology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
To that end, we rigorously formulate the problem of neural representations as a relation in space between stimulus-induced neural activity and the asymptotic dynamics of excitable cortical networks. ...
Nevertheless, no unifying account exists of how neurons in a recurrent cortical network learn to compute on temporally and spatially extended stimuli. ...
However, it remains mostly unclear how neurons in recurrent neural networks utilize neuronal plasticity to self-organize and to learn computing on temporally and spatially extended stimuli [2] [3] [4] ...
doi:10.1371/journal.pcbi.1003512
pmid:24651447
pmcid:PMC3961183
fatcat:6dft4ndyifeqvpcy73qnpxzxoi
Neural mechanisms underlying the temporal organization of naturalistic animal behavior
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We crystallize recent studies which converge on an emergent mechanistic theory of temporal variability based on attractor neural networks and metastable dynamics, arising from the coordinated interactions ...
Naturalistic animal behavior exhibits a strikingly complex organization in the temporal domain, whose variability stems from at least three sources: hierarchical, contextual, and stochastic. ...
Acknowledgments I would like to thank Zach Mainen, James Murray, Cris Niell, Matt Smear, Osama Ahmed, the participants of the Computational Neuroethology Workshop 2021 in Jackson, and the members of the ...
arXiv:2203.02151v1
fatcat:m3cnresdcndz7hhr2qizhrmxlu
An Attractor-Based Complexity Measurement for Boolean Recurrent Neural Networks
2014
PLoS ONE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We provide a novel refined attractor-based complexity measurement for Boolean recurrent neural networks that represents an assessment of their computational power in terms of the significance of their ...
attractor dynamics. ...
Acknowledgments The authors thank all the reviewers for their comments, and in particular the last reviewer for his suggestions concerning the proof of Proposition 2.
Author Contributions ...
doi:10.1371/journal.pone.0094204
pmid:24727866
pmcid:PMC3984152
fatcat:hfapzjg6qzav5pvch6u5j5crkq
Neural coordination can be enhanced by occasional interruption of normal firing patterns: A self-optimizing spiking neural network model
[article]
2014
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Here we demonstrate that it can be transferred to more biologically plausible neural networks by implementing a self-optimizing spiking neural network model. ...
The state space of a conventional Hopfield network typically exhibits many different attractors of which only a small subset satisfy constraints between neurons in a globally optimal fashion. ...
In order to construct a spiking neural network with conventional Hopfield dynamics, namely guaranteed convergence to a fixed-point attractor, we must have a fully interconnected recurrent network and a ...
arXiv:1409.0470v1
fatcat:vk4zucyl2vbx7bs7p5d6vitqie
Cognitive computation with autonomously active neural networks: an emerging field
[article]
2009
arXiv
pre-print
Preserved Fulltext
The Internet Archive has a preservation copy of this work in our general collections.
The file type is application/pdf.
The main emphasis will be then on two paradigmal neural network architectures showing continuously ongoing transient-state dynamics: saddle point networks and networks of attractor relics. ...
Self-active neural networks are confronted with two seemingly contrasting demands: a stable internal dynamical state and sensitivity to incoming stimuli. ...
Attractor relic networks and slow variables A trivial form of self-sustained neural activity occurs in attractor networks [39] . ...
arXiv:0901.3028v1
fatcat:alb6tmibmje77elxlxovv6xsva
Cognitive Computation with Autonomously Active Neural Networks: An Emerging Field
2009
Cognitive Computation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2016; you can also visit the original URL.
The file type is application/pdf.
The main emphasis will be then on two paradigmal neural network architectures showing continuously ongoing transient-state dynamics: saddle point networks and networks of attractor relics. ...
We show, that this dilemma can be solved by networks of attractor relics based on competitive neural dynamics, where the attractor relics compete on one side with each other for transient dominance, and ...
A trivial form of self-sustained neural activity occurs in attractor networks [39] . ...
doi:10.1007/s12559-008-9000-9
fatcat:ayldcifr2famrafdmuk32xetti
Chaotic itinerancy and its roles in cognitive neurodynamics
2015
Current Opinion in Neurobiology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Chaotic itinerancy is an autonomously excited trajectory through high-dimensional state space of cortical neural activity that causes the appearance of a temporal sequence of quasi-attractors. ...
In a cognitive neurodynamic aspect, quasi-attractors represent perceptions, thoughts and memories, chaotic trajectories between them with intelligent searches, such as history-dependent trial-and-error ...
Acknowledgments This work was partially supported by a Grant-in-Aid for Scientific Research on ...
doi:10.1016/j.conb.2014.08.011
pmid:25217808
fatcat:jj7qmbfcvne5bhxamb33jmzsri
Attractor and integrator networks in the brain
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2112.03978v2 fatcat:2mjr74v74ngztlxi5yiyutftxeOther Versions
In this review, we describe the singular success of attractor neural network models in describing how the brain maintains persistent activity states for working memory, error-corrects, and integrates noisy ...
We discuss the myriad potential uses of attractor dynamics for computation in the brain, and showcase notable examples of brain systems in which inherently low-dimensional continuous attractor dynamics ...
Mechanisms: The construction of neural attractors The basic principle underlying the formation of attractor states in neural circuits is strong recurrent positive feedback 2 , through lateral connectivity ...
arXiv:2112.03978v3
fatcat:b4bmol62brdhdnxnoj2lkc4yju
Improving the State Space Organization of Untrained Recurrent Networks
[chapter]
2009
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
In this work we demonstrate that the state space organization of untrained recurrent neural network can be significantly improved by choosing appropriate input representations. ...
Recurrent neural networks are frequently used in cognitive science community for modeling linguistic structures. ...
In [9] we have studied the state space organization of the recurrent neural network before and after training on three artificial languages. ...
doi:10.1007/978-3-642-02490-0_82
fatcat:oaw7c2uez5h7dm7a37642uczju
Chaotic Clustering: Fragmentary Synchronization of Fractal Waves
[chapter]
2011
Chaotic Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
In this paper we apply chaotic neural network to 2D and 3D clustering problem. L. ...
Structure complexity CNN does not have classical inputs -it is recurrent neural network with one layer of N neurons. ...
How to reference In order to correctly reference this scholarly work, feel free to copy and paste the following: ...
doi:10.5772/13995
fatcat:w7wpunlt35g4xj6ny5udv3fvpq
INFERNO: A Novel Architecture for Generating Long Neuronal Sequences with Spikes
[chapter]
2017
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
We name our architecture INFERNO for Iterative Free-Energy Optimization for Recurrent Neural Network. abstract environment. ...
As part of the principle of free-energy minimization proposed by Karl Friston, we propose a novel neural architecture to optimize the free-energy inherent to spiking recurrent neural networks to regulate ...
The neural control is done by controlling tiny variations injected into the recurrent network that can iteratively change its dynamics to make it to converge to attractors. ...
doi:10.1007/978-3-319-59072-1_50
fatcat:zr6gnq76j5htbjothkvx6l5f3u
Continuous attractors and oculomotor control
1998
Neural Networks
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2006; you can also visit the original URL.
The file type is application/pdf.
Because the stable states are arranged in a continuous dynamical attractor, the network can store a memory of eye position with analog neural encoding. ...
A recurrent neural network can possess multiple stable states, a property that many brain theories have implicated in learning and memory. ...
A synaptic learning rule based on presynaptic activity and retinal slip has been used to self-organize a network (Arnold and Robinson, 1997) . ...
doi:10.1016/s0893-6080(98)00064-1
pmid:12662748
fatcat:pbtes6eiprer5b3xm6dyyds4ha
On the Nature of Functional Differentiation: The Role of Self-Organization with Constraints
2022
Entropy
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Regarding the self-organized structure of neural systems, Warren McCulloch described the neural networks of the brain as being "heterarchical", rather than hierarchical, in structure. ...
In 2016, we proposed a theory for self-organization with constraints to clarify the neural mechanism of functional differentiation. ...
Dynamic Heterarchy As discussed above, the brain is a self-organizing system with both internal and external constraints, thus yielding the dynamically nonstationary activity of neural networks. ...
doi:10.3390/e24020240
pmid:35205534
pmcid:PMC8871511
fatcat:6gsuobuqc5b67l3ddcwhk432te
« Previous
Showing results 1 — 15 out of 3,182 results