Filters








1,156 Hits in 6.0 sec

Random Sketching, Clustering, and Short-Term Memory in Spiking Neural Networks

Yael Hitron, Nancy Lynch, Cameron Musco, Merav Parter, Michael Wagner
2020 Innovations in Theoretical Computer Science  
Technically, a contribution in our network design is the implementation of a short-term memory.  ...  Our analysis helps provide a theoretical understanding of these networks and lay a foundation for how random compression and input memorization may be implemented in biological neural networks.  ...  I T C S 2 0 2 0 23:10 Random Sketching, Clustering, and Short-Term Memory in Spiking Neural Networks Proof.  ... 
doi:10.4230/lipics.itcs.2020.23 dblp:conf/innovations/HitronLMP20 fatcat:s66fguy7kbd5plweptczy3xide

Coupled neural associative memories

Amin Karbasi, Amir Hesam Salavati, Amin Shokrollahi
2013 2013 IEEE Information Theory Workshop (ITW)  
We propose a novel architecture to design a neural associative memory that is capable of learning a large number of patterns and recalling them later in presence of noise.  ...  It is based on dividing the neurons into local clusters and parallel plains, an architecture that is similar to the visual cortex of macaque brain.  ...  Vahid Aref, and Dr. Seyed Hamed Hassani for their helpful discussions.  ... 
doi:10.1109/itw.2013.6691267 dblp:conf/itw/KarbasiSS13 fatcat:vcovodrjrjc3bjw5zjhrxuqn64

Letting the Brain Speak for itself [article]

Gerhard Werner
2011 arXiv   pre-print
Accordingly, local cooperative processes, intrinsic to neural structures and of fractal nature, call for applying Fractional Calculus and models of Random Walks in Theoretical Neuroscience studies.  ...  Metaphors of Computation and Information tended to detract attention from the intrinsic modes of neural system functions, uncontaminated by the observer's role for collection and interpretation of experimental  ...  models of Random Walks with long-term memory: the overriding issue is the fractality in the context of Complex System Dynamics.  ... 
arXiv:1107.4028v1 fatcat:gumi4p3e3nep7k3c26xwnnklsi

Letting the Brain Speak for Itself

Gerhard Werner
2011 Frontiers in Physiology  
Accordingly, local cooperative processes, intrinsic to neural structures, and of fractal nature, call for applying Fractional Calculus and models of Random Walks with long-term memory in Theoretical Neuroscience  ...  Metaphors of Computation and Information tended to detract attention from the intrinsic modes of neural system functions, uncontaminated by the observer's role in collection, and interpretation of experimental  ...  models of Random Walks with long-term memory: the overriding issue is the fractality in the context of Complex System Dynamics.  ... 
doi:10.3389/fphys.2011.00060 pmid:21960973 pmcid:PMC3178033 fatcat:xhbmd5v3a5gqdeiwcs2wii2wdm

Noise Helps Optimization Escape From Saddle Points in the Synaptic Plasticity

Ying Fang, Zhaofei Yu, Feng Chen
2020 Frontiers in Neuroscience  
Our study provides a new learning framework for the brain and sheds new light on deep noisy spiking neural networks.  ...  Motivated by these arguments, we propose one biologically plausible noise structure and demonstrate that noise can efficiently improve the optimization performance of spiking neural networks based on stochastic  ...  Simulation results show that noisy spiking neural networks have higher learning accuracy, and spike responses had a more obvious preference pattern for random spike train inputs.  ... 
doi:10.3389/fnins.2020.00343 pmid:32410937 pmcid:PMC7201302 fatcat:tqntz3j5e5dd5pzks3da5ioopq

Shallow Unorganized Neural Networks Using Smart Neuron Model for Visual Perception

Richard Jiang, Danny Crookes
2019 IEEE Access  
INDEX TERMS Unorganized neural networks, Turing's type-B unorganized machine, smart neuron model, early vision, unsupervised visual processing.  ...  The recent success of Deep Neural Networks (DNNs) has revealed the significant capability of neural computing in many challenging applications.  ...  Furthermore, long term and short term learning divides the brain's learning into two distinct capabilities.  ... 
doi:10.1109/access.2019.2946422 fatcat:bjtutko7kvharlel4gmkd3np2e

Optoelectronic Intelligence [article]

Jeffrey M. Shainline
2020 arXiv   pre-print
For large neural systems capable of general intelligence, the attributes of photonics for communication and electronics for computation are complementary and interdependent.  ...  For computation, the inherent nonlinearities, high speed, and low power consumption of Josephson circuits are conducive to complex neural functions.  ...  Structurally, this information processing is facilitated by networks with a high clustering coefficient yet also an average path length nearly as short as a random graph [26] .  ... 
arXiv:2010.08690v1 fatcat:6zrpdxj4bfacld2ewf6lonjnzq

Shallow Unorganized Neural Networks using Smart Neuron Model for Visual Perception [article]

Richard Jiang, Danny Crookes
2019 arXiv   pre-print
The recent success of Deep Neural Networks (DNNs) has revealed the significant capability of neural computing in many challenging applications.  ...  In this paper, we propose a new computational model, namely shallow unorganized neural networks (SUNNs), in contrast to ANNs/DNNs.  ...  Furthermore, long term and short term learning divides the brain's learning into two distinct capabilities.  ... 
arXiv:1907.09050v2 fatcat:mwmfj3sbyvfjth3dhniqjjwzaa

Spatiotemporal Patterns in Neurobiology: An Overview for Future Artificial Intelligence [article]

Sean Knight, Navjot Gadda
2022 arXiv   pre-print
Here we review several classes of models including spiking neurons, integrate and fire neurons with short term plasticity (STP), conductance based integrate-and-fire models with STP, and population density  ...  In recent years, there has been increasing interest in developing models and tools to address the complex patterns of connectivity found in brain tissue.  ...  short term plasticity type synapses together.  ... 
arXiv:2203.15415v2 fatcat:apgrca4n35f7jmrcmd5hfkehxa

Organization and priming of long-term memory representations with two-phase plasticity [article]

Jannik Luboeinski, Christian Tetzlaff
2021 bioRxiv   pre-print
To this end, we employ a biologically detailed neural network model of spiking neurons featuring STC, which models the learning and consolidation of long-term memory representations.  ...  To link this mechanism to long-term memory and thereby to the level of behavior, its dynamics on the level of recurrent networks have to be understood.  ...  The research was funded by the German Research Foundation (CRC1286, project C1, project #419866478) and by the H2020 -FETPROACT project Plan4Act (#732266).  ... 
doi:10.1101/2021.04.15.439982 fatcat:jdebnacklfhfxpvgty6hqnn64q

Computing with Spiking Neuron Networks [chapter]

Hélène Paugam-Moisy, Sander Bohte
2012 Handbook of Natural Computing  
Spiking Neuron Networks (SNNs) are often referred to as the 3 rd generation of neural networks.  ...  The computational power of SNNs is addressed in Section 3 and the problem of learning in networks of spiking neurons is tackled in Section 4, with insights into the tracks currently explored for solving  ...  In the second or minute timescale, the weight changes are denoted as Short Term Potentiation (STP) and Short Term Depression (STD).  ... 
doi:10.1007/978-3-540-92910-9_10 fatcat:uixmvc27zjgirg5oobqaqwccpe

Toward Reflective Spiking Neural Networks Exploiting Memristive Devices

Valeri A. Makarov, Sergey A. Lobov, Sergey Shchanikov, Alexey Mikhaylov, Viktor B. Kazantsev
2022 Frontiers in Computational Neuroscience  
In this study, we forecast that spiking neural networks (SNNs) can achieve the next qualitative leap.  ...  Thus, memristive devices are a good candidate for implementing in-memory and in-sensor computing.  ...  Figure 3C illustrates a sketch of how random data points appear in the HD space.  ... 
doi:10.3389/fncom.2022.859874 pmid:35782090 pmcid:PMC9243340 fatcat:ulpwch56gfhejbvz6etjbw2csi

Attention and working memory: a dynamical model of neuronal activity in the prefrontal cortex

Gustavo Deco, Edmund T. Rolls
2003 European Journal of Neuroscience  
We describe here an integrate-and-®re network model to explain and investigate the different types of working-memory-related neuronal activity observed.  ...  These neurons provide a neural substrate for mapping stimulus and response in a¯exible, context-or rule-dependent, fashion.  ...  the short-term memory delay period.  ... 
doi:10.1046/j.1460-9568.2003.02956.x pmid:14622200 fatcat:s774jy2q3zhyxmo2bldx4s44de

Attractor Hypothesis of Associative Cortex: Insights from a Biophysically Detailed Network Model [chapter]

Mikael Lundqvist, Pawel Herman, Anders Lansner
2013 Functional Brain Mapping and the Endeavor to Understand the Working Brain  
Author details Mikael Lundqvist * , Pawel Herman and Anders Lansner KTH and Stockholm University, Stockholm, Sweden  ...  A cluster of minicolumns, spanning a few hundred microns, constitutes a hypercolumn in the network.  ...  Attractor networks have several dynamical attractors, to which similar activity patterns in terms of a combination of specific active and inactive units are attracted.  ... 
doi:10.5772/56229 fatcat:ykw6k3r2mjgu7bzw7gn5zjvf44

Identification of excitatory-inhibitory links and network topology in large-scale neuronal assemblies from multi-electrode recordings

Vito Paolo Pastore, Paolo Massobrio, Aleksandar Godjoski, Sergio Martinoia, Daniele Marinazzo
2018 PLoS Computational Biology  
The method is applicable to both in vitro and in vivo spike data recordings.  ...  ) microtransducer arrays coupled to in vitro neural populations are presented.  ...  Mariateresa Tedesco (Brunella) for providing excellent cortical cultures and for her constant support and advice during all the experimental sessions.  ... 
doi:10.1371/journal.pcbi.1006381 pmid:30148879 fatcat:nlr4ir3v3bednpw4ssb5yczmpq
« Previous Showing results 1 — 15 out of 1,156 results