Filters








56,834 Hits in 6.8 sec

On the Necessity of U-Shaped Learning

Lorenzo Carlucci, John Case
<span title="">2013</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7mhd2nftwbcuddio7gdfyoy3iq" style="color: black;">Topics in Cognitive Science</a> </i> &nbsp;
We present results about the necessity of U-shaped learning in classical models of learning as well as in models with bounds on the memory of the learner.  ...  The pattern emerges that, for parameterized, cognitively relevant learning criteria, beyond very few initial parameter values, U-shapes are necessary for full learning power!  ...  Here is a collection of master open questions (so far) regarding the necessity of U-shaped learning for humanly plausible criteria with memory limitations. Suppose m + n > 0.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/tops.12002">doi:10.1111/tops.12002</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/23335574">pmid:23335574</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l7wgkacx75asvoelwqohjs7wzu">fatcat:l7wgkacx75asvoelwqohjs7wzu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170812093920/https://www.eecis.udel.edu/~case/papers/pr2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6c/12/6c128e2a8058819ad031894989ceed8126136fc3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/tops.12002"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Guest Editors' foreword

Marcus Hutter, Frank Stephan, Vladimir Vovk, Thomas Zeugmann
<span title="">2013</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/elaf5sq7lfdxfdejhkqbtz6qoq" style="color: black;">Theoretical Computer Science</a> </i> &nbsp;
Case and Kötzing investigate in their paper Memory-limited non-U-shaped learning with solved open problems the question of when U-shaped learning behavior can be avoided without losing learning power.  ...  But for various other learning criteria, in particular those with limitations of the long term memory, this question of whether or not U-shaped learning is unavoidable remained open.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.tcs.2012.10.007">doi:10.1016/j.tcs.2012.10.007</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ciit7zasgzgytfxx66tzb5onku">fatcat:ciit7zasgzgytfxx66tzb5onku</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808225939/http://www.hutter1.net/publ/alt10tcs.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b7/ce/b7cedf9791b1c186cfc98f9b5f608d13b39b7d30.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.tcs.2012.10.007"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Jog my shape memory: dynamics as a challenge in mathematical materials science

J. Zimmer
<span title="2006-12-15">2006</span> <i title="The Royal Society"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ercgg4vn2fenngurcnadfzdfri" style="color: black;">Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences</a> </i> &nbsp;
The challenge is to understand how the effects on one scale influence those on another.  ...  I am very grateful to him for the time they invested, as well as for teaching me how to prepare samples. Sincere thanks are expressed to Hans-Georg Zimmer for drawing figures 2, 3 and 4.  ...  The author is particularly grateful for the assistance received from Frank Hammett of the Department of Mechanical Engineering at the University of Bath in the preparation of micrographs shown in figure  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1098/rsta.2006.1898">doi:10.1098/rsta.2006.1898</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/17090460">pmid:17090460</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/s3ud7m7z7fc2djqn4oqroizpi4">fatcat:s3ud7m7z7fc2djqn4oqroizpi4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170922000723/http://opus.bath.ac.uk/7010/1/martensite2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/49/d4/49d486ce5ac18b0a771bfc4427b1f780ab4e5fe4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1098/rsta.2006.1898"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Brain-Inspired Learning on Neuromorphic Substrates [article]

Friedemann Zenke, Emre O. Neftci
<span title="2020-10-22">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, training on neuromorphic substrates creates significant challenges due to the offline character and the required non-local computations of gradient-based learning algorithms.  ...  learning rules for training Spiking Neural Networks (SNNs).  ...  Here, we focus on two solutions to maintain G t sparse. The first solution is to work with sparse H E matrices, meaning in the case of a single layer RNN a sparse matrix V with few non-zero entries.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.11931v1">arXiv:2010.11931v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/e7bwgrmynvgmfkuordiqb3zusq">fatcat:e7bwgrmynvgmfkuordiqb3zusq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201029000205/https://arxiv.org/pdf/2010.11931v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cf/07/cf07b84788356c5587c687c069945f5037476489.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.11931v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Dynamic neural fields as a step toward cognitive neuromorphic architectures

Yulia Sandamirskaya
<span title="">2014</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wrk3kouosrhcxiprcbguskdipu" style="color: black;">Frontiers in Neuroscience</a> </i> &nbsp;
These specific mechanisms include the stabilization of working memory, the coupling of sensory systems to motor dynamics, intentionality, and autonomous learning.  ...  I further demonstrate how all these elements may be integrated into a unified architecture to generate behavior and autonomous learning.  ...  However, there are still open questions on the way toward cognitive processing with hardware WTAs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2013.00276">doi:10.3389/fnins.2013.00276</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/24478620">pmid:24478620</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC3898057/">pmcid:PMC3898057</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5eapyb6t2nhpjjyknzsjia4equ">fatcat:5eapyb6t2nhpjjyknzsjia4equ</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171006023431/http://publisher-connector.core.ac.uk/resourcesync/data/Frontiers/pdf/008/aHR0cDovL2pvdXJuYWwuZnJvbnRpZXJzaW4ub3JnL2FydGljbGUvMTAuMzM4OS9mbmlucy4yMDEzLjAwMjc2L3BkZg%3D%3D.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/81/bc/81bc1a88dfdfc2a938de8546f19ca70ae278919f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnins.2013.00276"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3898057" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Editors' Introduction [chapter]

Sanjay Jain, Rémi Munos, Frank Stephan, Thomas Zeugmann
<span title="">2013</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In other models, the learner is more active, asking questions or learning from its actions.  ...  He formulates a general framework for a large class of learning algorithms for such languages and, using this framework, he reviews Angluin's classical LSTAR algorithm and compares it with various contemporary  ...  John Case and Timo Kötzing investigate in their paper Solutions to Open Questions for Non-U-Shaped Learning with Memory Limitations the question when U-shaped learning behaviour can be avoided without  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-40935-6_1">doi:10.1007/978-3-642-40935-6_1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pchrsvhjezfbvh6dfplqhxhgcy">fatcat:pchrsvhjezfbvh6dfplqhxhgcy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190220174937/http://pdfs.semanticscholar.org/2bd4/b0d4a7956c68d7cbcadf4315eb22719ca09a.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2b/d4/2bd4b0d4a7956c68d7cbcadf4315eb22719ca09a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-40935-6_1"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Synthetic biology routes to bio-artificial intelligence

Darren N. Nesbeth, Alexey Zaikin, Yasushi Saka, M. Carmen Romano, Claudiu V. Giuraniuc, Oleg Kanakov, Tetyana Laptyeva
<span title="2016-11-30">2016</span> <i title="Portland Press Ltd."> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/y5hbc7qpnjd73b3umji6wrwbce" style="color: black;">Essays in Biochemistry</a> </i> &nbsp;
The design of synthetic gene networks (SGNs) has advanced to the extent that novel genetic circuits are now being tested for their ability to recapitulate archetypal learning behaviours first defined in  ...  In addition to designed SGNs, we also consider the option to establish conditions in which a population of SGNs can evolve diversity in order to better contend with complex input data.  ...  A key question is whether learning in single cells occurs in a manner analogous to multicellular systems, or with an architecture that is predetermined by genetically encoded programs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1042/ebc20160014">doi:10.1042/ebc20160014</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/27903825">pmid:27903825</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC5264507/">pmcid:PMC5264507</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zzrhdut2tbb3hi5tubjhz3qqbe">fatcat:zzrhdut2tbb3hi5tubjhz3qqbe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170923012200/http://discovery.ucl.ac.uk/1531681/1/381.full.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1f/51/1f513611cabbf9bb54bc9332872a1e5f52b7ade4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1042/ebc20160014"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5264507" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Optimal memory-aware backpropagation of deep join networks

Olivier Beaumont, Julien Herrmann, Guillaume Pallez (Aupy), Alena Shilova
<span title="2020-01-20">2020</span> <i title="The Royal Society"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ercgg4vn2fenngurcnadfzdfri" style="color: black;">Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences</a> </i> &nbsp;
In this work, we propose to use techniques from memory-aware scheduling and automatic differentiation (AD) to execute a backpropagation graph with a bounded memory requirement at the cost of extra recomputations  ...  The networks encountered in practice in the context of deep learning are much more diverse, both in terms of shape and heterogeneity.  ...  All authors participated to the model, derivations of theoretical results and writing of the manuscript. JH implemented the main algorithm, AS and GP performed the evaluations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1098/rsta.2019.0049">doi:10.1098/rsta.2019.0049</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/31955681">pmid:31955681</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7015292/">pmcid:PMC7015292</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rhugm5fgp5cwpawfxwsomu3m3m">fatcat:rhugm5fgp5cwpawfxwsomu3m3m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200508012830/https://hal.inria.fr/hal-02401105/document" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bb/0a/bb0a4e4f7b894949ca0d05fae4217845f09ebdd3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1098/rsta.2019.0049"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7015292" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Vision System for AGI: Problems and Directions [chapter]

Alexey Potapov, Sergey Rodionov, Maxim Peterson, Oleg Scherbakov, Innokentii Zhdanov, Nikolai Skorobogatko
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
We discuss some existing generative and discriminative models and demonstrate their insufficiency for our purposes. Finally, we discuss some architectural dilemmas and open questions.  ...  What frameworks and architectures are necessary to create a vision system for AGI? In this paper, we propose a formal model that states the task of perception within AGI.  ...  Thus, discriminative models should not be necessarily capable of automatic learning of invariants, but the question whether to expand the existing formal neural models or not remains open.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-97676-1_18">doi:10.1007/978-3-319-97676-1_18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jizoiuoof5dkjhhah4prffeli4">fatcat:jizoiuoof5dkjhhah4prffeli4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190307043616/http://pdfs.semanticscholar.org/d15b/6ff3cb38be6d84cd1a167932451cf9e929ae.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d1/5b/d15b6ff3cb38be6d84cd1a167932451cf9e929ae.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-97676-1_18"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computing [article]

André Röhm and Daniel J. Gauthier and Ingo Fischer
<span title="2021-10-01">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we show that the ability to learn the dynamics of a complex system can be extended to systems with co-existing attractors, here a 4-dimensional extension of the well-known Lorenz chaotic  ...  Reservoir computers are powerful tools for chaotic time series prediction.  ...  For systems with only a single training data set, independent error estimation remains an open question for now.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.04074v2">arXiv:2108.04074v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gndlu5fm4je7zgq2yjmaiawo3i">fatcat:gndlu5fm4je7zgq2yjmaiawo3i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211009232451/https://arxiv.org/pdf/2108.04074v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3f/07/3f07b314b6e5c26be891f9f39c9142dff5b4b799.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2108.04074v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Dataset and Architecture for Visual Reasoning with a Working Memory [article]

Guangyu Robert Yang, Igor Ganichev, Xiao-Jing Wang, Jonathon Shlens, David Sussillo
<span title="2018-07-20">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
COG is much simpler than the general problem of video analysis, yet it addresses many of the problems relating to visual and logical reasoning and memory -- problems that remain challenging for modern  ...  Inspired by a rich tradition of visual reasoning and memory in cognitive psychology and neuroscience, we developed an artificial, configurable visual question and answer dataset (COG) to parallel experiments  ...  One avenue for studying visual reasoning has been Visual Question Answering (VQA) datasets where a model learns to correctly answer challenging natural language questions about static Fig. 1 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.06092v2">arXiv:1803.06092v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/voujsn7lqjfbhd7gzofnaqc7mq">fatcat:voujsn7lqjfbhd7gzofnaqc7mq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826234231/https://arxiv.org/pdf/1803.06092v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/28/53/285356448b8d6e4bd84c67758502a76336f30b0e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.06092v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Long-term Potentiation Decay and Poor Long-lasting Memory Process in the Wild Rodents Proechimys from Brazil's Amazon Rainforest

Marcia J. Guimarães Marques, Selvin Z. Reyes-Garcia, José E. Marques-Carneiro, Leonardo B. Lopes-Silva, Monica L. Andersen, Esper A. Cavalheiro, Fulvio A. Scorza, Carla A. Scorza
<span title="2018-01-23">2018</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/sx3lvh2nmvah7ilqdbdicsjcku" style="color: black;">Frontiers in Behavioral Neuroscience</a> </i> &nbsp;
Nevertheless, why early-phase LTP in Proechimys decays very rapidly remains to be elucidated.  ...  Memory and LTP of Proechimys period. These findings suggest a link between the LTP decay and the lack of 24-h long-lasting memory process in Proechimys.  ...  ACKNOWLEDGMENTS This manuscript is dedicated to the memory of the remarkable scientist and dear friend Professor Roberto Frussa-Filho, who developed the plus-maze discriminative avoidance model used in  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnbeh.2018.00002">doi:10.3389/fnbeh.2018.00002</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29410617">pmid:29410617</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC5787059/">pmcid:PMC5787059</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sba2svwx3zfozffa5a4fxxdkem">fatcat:sba2svwx3zfozffa5a4fxxdkem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190218143929/http://pdfs.semanticscholar.org/0cfb/b07c504fbd5a680b5a8c7e1e4fdd49c184b9.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0c/fb/0cfbb07c504fbd5a680b5a8c7e1e4fdd49c184b9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fnbeh.2018.00002"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5787059" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Brain-Inspired Learning on Neuromorphic Substrates

Friedemann Zenke, Emre O. Neftci
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/yfvtieuumfamvmjlc255uckdlm" style="color: black;">Proceedings of the IEEE</a> </i> &nbsp;
learning rules for training spiking neural networks (SNNs).  ...  This article provides a mathematical framework for the design of practical online learning algorithms for neuromorphic substrates.  ...  Memory is generally a limiting factor in neuromorphic hardware. In SNNs, the need for online learning in combination with such capacity limits makes forward-mode accumulation particularly compelling.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jproc.2020.3045625">doi:10.1109/jproc.2020.3045625</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pelkbpbg5jg7pjyvkvtpgrt2su">fatcat:pelkbpbg5jg7pjyvkvtpgrt2su</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210718031232/https://ieeexplore.ieee.org/ielx7/5/9420072/09317744.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c9/c6/c9c6a70c30cd3b2976d2616adeb5158ab15296d8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/jproc.2020.3045625"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

A model for non-monotonic intensity coding

J. Nehrkorn, H. Tanimoto, A. V. M. Herz, A. Yarali
<span title="2015-05-01">2015</span> <i title="The Royal Society"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/b4xnwzxv5re5rbc2gcpilgy5iy" style="color: black;">Royal Society Open Science</a> </i> &nbsp;
A suitable system to study this general question is odour-intensity learning.  ...  To support intensityspecific memories, however, it is critical to have different neurons with non-nested tuning curves peaking at different values along the intensity axis (figures 2 versus 3).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1098/rsos.150120">doi:10.1098/rsos.150120</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/26064666">pmid:26064666</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC4453257/">pmcid:PMC4453257</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tdg2esabo5hr7l7qsezrj3vip4">fatcat:tdg2esabo5hr7l7qsezrj3vip4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180720074042/https://epub.ub.uni-muenchen.de/34302/1/10.1098_rsos.150120.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dd/3f/dd3fa0ccbb6a63330aa661801c363894f5e49998.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1098/rsos.150120"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4453257" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

An Influence of Nonlinearities to Storage Capacity of Neural Networks

Algis Garliauskas
<span title="">2005</span> <i title="Vilnius University Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2euqyspe25eahoco4ofscpbnai" style="color: black;">Informatica</a> </i> &nbsp;
We suppose an alternative MFT with deterministic features instead of stochastic nature of searching a solution a set of large number equations.  ...  The general procedure of averaging the quenched random states in the fully-connected networks for MFT, as usually, is based on the Boltzmann Machine learning.  ...  The solution remains absolutely stable. The state configuration of this minimum endows the network with abilities to the embedded memory.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15388/informatica.2005.091">doi:10.15388/informatica.2005.091</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nmpfeh6ffbehnfkfrrs4srrxme">fatcat:nmpfeh6ffbehnfkfrrs4srrxme</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200506123347/https://informatica.vu.lt/journal/INFORMATICA/article/1043/file/pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5e/12/5e1219adf955cafda59b833456ecd3f9b9e23881.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15388/informatica.2005.091"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 56,834 results