Filters








8,170 Hits in 7.0 sec

Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study [article]

Samuel Ritter, David G.T. Barrett, Adam Santoro, Matt M. Botvinick
<span title="2017-06-29">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Deep neural networks (DNNs) have achieved unprecedented performance on a wide range of complex tasks, rapidly outpacing our understanding of the nature of their solutions.  ...  These results demonstrate the capability of tools from cognitive psychology for exposing hidden computational properties of DNNs, while concurrently providing us with a computational model for human word  ...  Acknowledgements We would like to thank Linda Smith and Charlotte Wozniak for providing the Cognitive Psychology probe dataset; Charles Blundell for reviewing our paper prior to submission; Oriol Vinyals  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1706.08606v2">arXiv:1706.08606v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dww7fe7mf5b3ve4qm7nxmobrta">fatcat:dww7fe7mf5b3ve4qm7nxmobrta</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191013163542/https://arxiv.org/pdf/1706.08606v2.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/39/fb/39fb9fa2615620f043084a2ecbbdb1a1f8c707c9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1706.08606v2" 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>

Potentials and Limitations of Deep Neural Networks for Cognitive Robots [article]

Doreen Jirak, Stefan Wermter
<span title="2018-05-02">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Although Deep Neural Networks reached remarkable performance on several benchmarks and even gained scientific publicity, they are not able to address the concept of cognition as a whole.  ...  Then, we identify crucial settings for cognitive robotics where deep neural networks have as yet only contributed little compared to the challenges in cognitive robotics.  ...  Joining DNNs with cognitive psychology may open the way to further investigate the positive as well as negative aspects of biases in human learning, complementing behavioral studies which found the basis  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.00777v1">arXiv:1805.00777v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/d734apeprbgaxjbom4hixrmvie">fatcat:d734apeprbgaxjbom4hixrmvie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825085326/https://arxiv.org/pdf/1805.00777v1.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/81/1b/811bdfe89db0e7fb9e08d536094687e1a3a9e8ca.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.00777v1" 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>

Learning Inductive Biases with Simple Neural Networks [article]

Reuben Feinman, Brenden M. Lake
<span title="2018-06-13">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A recent study found that deep neural networks optimized for object recognition develop the shape bias (Ritter et al., 2017), an inductive bias possessed by children that plays an important role in early  ...  We find that simple neural networks develop a shape bias after seeing as few as 3 examples of 4 object categories.  ...  In a recent study, Ritter et al. (2017) found that performance-optimized deep neural networks (DNNs) develop the shape bias when trained on the popular ImageNet object recognition dataset consisting  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.02745v2">arXiv:1802.02745v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mwxzl3rig5hkhp3sapqtvsrgby">fatcat:mwxzl3rig5hkhp3sapqtvsrgby</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200831203140/https://arxiv.org/pdf/1802.02745v2.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/6a/41/6a41a61858f14815335de28bb5261563eb8fdbfc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.02745v2" 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>

Mutual exclusivity as a challenge for deep neural networks [article]

Kanishk Gandhi, Brenden M. Lake
<span title="2020-10-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We demonstrate that there is a compelling case for designing neural networks that reason by mutual exclusivity, which remains an open challenge.  ...  In this paper, we investigate whether or not standard neural architectures have an ME bias, demonstrating that they lack this learning assumption.  ...  By representing the structure of the data more accurately allows for quicker generalization, there is also potential for models to learn a wider range of undesirable biases present in the training data  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.10197v3">arXiv:1906.10197v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lco3zynzivdjjaiuh67lmm24su">fatcat:lco3zynzivdjjaiuh67lmm24su</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201025133413/https://arxiv.org/pdf/1906.10197v3.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/90/3f/903f6b4bea01a0be5cc6a5f55fa70683ca9edbb5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.10197v3" 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>

Network Neuroscience and the Adapted Mind: Rethinking the Role of Network Theories in Evolutionary Psychology

Nassim Elimari, Gilles Lafargue
<span title="2020-09-25">2020</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5r5ojcju2repjbmmjeu5oyawti" style="color: black;">Frontiers in Psychology</a> </i> &nbsp;
Evolutionary psychology is the comprehensive study of cognition and behavior in the light of evolutionary theory, a unifying paradigm integrating a huge diversity of findings across different levels of  ...  Since natural selection shaped the brain into a functionally organized system of interconnected neural structures rather than an aggregate of separate neural organs, the network-based account of anatomo-functional  ...  It is interesting to note that, from the first writings of pioneers in evolutionary psychology, a focus is made on mechanistic explanations for how neural circuitry produces cognition and behaviors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fpsyg.2020.545632">doi:10.3389/fpsyg.2020.545632</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33101120">pmid:33101120</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC7545950/">pmcid:PMC7545950</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7idrahc7znhh7h425yqas6cusi">fatcat:7idrahc7znhh7h425yqas6cusi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200926152536/https://fjfsdata01prod.blob.core.windows.net/articles/files/545632/pubmed-zip/.versions/1/.package-entries/fpsyg-11-545632/fpsyg-11-545632.pdf?sv=2018-03-28&amp;sr=b&amp;sig=VbpF8DFSg1mSmkK5NriT%2B21kPG29gd8ywvaz%2Brzt%2Bw4%3D&amp;se=2020-09-26T15%3A26%3A05Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27fpsyg-11-545632.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/98/91/9891c7a25651fe6d451ea5518213b8953babae45.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/fpsyg.2020.545632"> <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/PMC7545950" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Can Deep Neural Networks Match the Related Objects?: A Survey on ImageNet-trained Classification Models [article]

Han S. Lee, Heechul Jung, Alex A. Agarwal, Junmo Kim
<span title="2017-09-12">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Deep neural networks (DNNs) have shown the state-of-the-art level of performances in wide range of complicated tasks.  ...  In this paper, we investigate the limitation of DNNs in image classification task and verify it with the method inspired by cognitive psychology.  ...  In addition, one recent research studied the shape bias in DNN learning through cognitive psychology-inspired approaches (Ritter et al. 2017) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.03806v1">arXiv:1709.03806v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fxdrhyiprnb25ca6kyvcaii7m4">fatcat:fxdrhyiprnb25ca6kyvcaii7m4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829020640/https://arxiv.org/pdf/1709.03806v1.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/4d/f8/4df8da4fcd94973a82f631140b50619514b28322.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.03806v1" 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>

Capturing the objects of vision with neural networks [article]

Benjamin Peters, Nikolaus Kriegeskorte
<span title="2021-09-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The cognitive literature provides a starting point for the development of new experimental tasks that reveal mechanisms of human object perception and serve as benchmarks driving development of deep neural  ...  Deep neural network (DNN) models of visual object recognition, by contrast, remain largely tethered to the sensory input, despite achieving human-level performance at labeling objects.  ...  Modern deep neural networks scale up many of the known neural network mechanisms.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03351v1">arXiv:2109.03351v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wlkibi4xrvgtrnrgl5ywit7pma">fatcat:wlkibi4xrvgtrnrgl5ywit7pma</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210914150213/https://arxiv.org/pdf/2109.03351v1.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/be/8b/be8b085c31abf113a7b2368d53f862208d586ed5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03351v1" 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>

Assessing Shape Bias Property of Convolutional Neural Networks [article]

Hossein Hosseini, Baicen Xiao, Mayoore Jaiswal, Radha Poovendran
<span title="2018-03-21">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Convolutional Neural Networks (CNNs) are also designed to take into account the spatial structure of image data.  ...  In fact, experiments on image datasets, consisting of triples of a probe image, a shape-match and a color-match, have shown that one-shot learning models display shape bias as well.  ...  Deep neural networks are known to be capable of approximating any measurable function given sufficient capacity [14, 15] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.07739v1">arXiv:1803.07739v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p5mwz6lzfzf37i3u76ojjmfoyu">fatcat:p5mwz6lzfzf37i3u76ojjmfoyu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191018025222/https://arxiv.org/pdf/1803.07739v1.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/2c/01/2c011c9f2fd228ec7e45f012c284da58ff666a8c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.07739v1" 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>

Critical branching neural networks

Christopher T. Kello
<span title="">2013</span> <i title="American Psychological Association (APA)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7dgw55nuivbwlepq7ytxkik6ny" style="color: black;">Psychological review</a> </i> &nbsp;
A spiking neural network model is presented that self-tunes to critical branching and, in doing so, simulates observed scaling laws as pervasive to neural and behavioral activity.  ...  Issues and questions raised by the model and its results are discussed from the perspectives of physics, neuroscience, computer and information sciences, and psychological and cognitive sciences.  ...  such bias for inhibitory weights.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1037/a0030970">doi:10.1037/a0030970</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/23356781">pmid:23356781</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q6lx6ndggffypatdy6p73b5oii">fatcat:q6lx6ndggffypatdy6p73b5oii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190219174849/http://pdfs.semanticscholar.org/1c40/ee1820153f5be265a73dc5c7becc2df2f005.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/1c/40/1c40ee1820153f5be265a73dc5c7becc2df2f005.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1037/a0030970"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure

Been Kim, Emily Reif, Martin Wattenberg, Samy Bengio, Michael C. Mozer
<span title="2021-04-09">2021</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/qnivjps37bh57mxnribuwdp7e4" style="color: black;">Computational Brain &amp; Behavior</a> </i> &nbsp;
We demonstrate that a state-of-the-art convolutional neural network, trained to classify natural images, exhibits closure on synthetic displays of edge fragments, as assessed by similarity of internal  ...  This finding provides further support for the hypothesis that the human perceptual system is even more elegant than the Gestaltists imagined: a single law—adaptation to the statistical structure of the  ...  Acknowledgements We are grateful to Mary Peterson and three anonymous reviewers for insightful feedback on earlier drafts of the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s42113-021-00100-7">doi:10.1007/s42113-021-00100-7</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gmg7pwahcvczvgaonov4try6d4">fatcat:gmg7pwahcvczvgaonov4try6d4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210718084840/https://link.springer.com/content/pdf/10.1007/s42113-021-00100-7.pdf?error=cookies_not_supported&amp;code=50d4fe29-6c38-4a78-bd9f-f98b2a1dc073" 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/d1/39/d1390fb332477749f2157b2ae75b9d7c0874de95.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s42113-021-00100-7"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

From convolutional neural networks to models of higher‐level cognition (and back again)

Ruairidh M. Battleday, Joshua C. Peterson, Thomas L. Griffiths
<span title="2021-03-22">2021</span> <i title="Wiley"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hs2remnzfbfmnf33cof2z4ajhi" style="color: black;">Annals of the New York Academy of Sciences</a> </i> &nbsp;
One consequence of these insights is a toolkit for the integration of cognitively motivated constraints back into CNN training paradigms in computer vision and machine learning, and we review cases where  ...  A second consequence is a roadmap for how CNNs and cognitive models can be more fully integrated in the future, allowing for flexible end-to-end algorithms that can learn representations from data while  ...  Deep and convolutional neural networks Artificial neural networks have a long connection to cognitive neuroscience, both as models of neurons and as a brain-compatible computing paradigm.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/nyas.14593">doi:10.1111/nyas.14593</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33754368">pmid:33754368</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/htjtw7if7zeuhop3o6mzznk4wy">fatcat:htjtw7if7zeuhop3o6mzznk4wy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210716112942/https://nyaspubs.onlinelibrary.wiley.com/doi/pdfdirect/10.1111/nyas.14593" 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/64/e1/64e1d2d77b93bacf1200a714194283093698bf05.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1111/nyas.14593"> <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 constructive neural-network approach to modeling psychological development

Thomas R. Shultz
<span title="">2012</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ifofwd73uvgq3dio2g6pim5lzy" style="color: black;">Cognitive development</a> </i> &nbsp;
Although many computational models of psychological development involve only learning, this paper examines the advantages of allowing artificial neural networks to grow as well as learn in such simulations  ...  Results show no differences in comparison to previous conservation simulations done with standard cascade-correlation except for fewer network layers and connections with SDCC.  ...  Acknowledgements This work is supported by a grant from the Natural Sciences and Engineering Research Council of Canada.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cogdev.2012.08.002">doi:10.1016/j.cogdev.2012.08.002</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uef67fiu4fhi7ghxjeedn5shx4">fatcat:uef67fiu4fhi7ghxjeedn5shx4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170811232433/http://cseweb.ucsd.edu/%7Egary/PAPER-SUGGESTIONS/shultz-attn-perf-2006.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/b9/aa/b9aa73278e1317f8351ba1b1b3a2921f86b94101.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.cogdev.2012.08.002"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Bio-instantiated recurrent neural networks: Integrating neurobiology-based network topology in artificial networks

Alexandros Goulas, Fabrizio Damicelli, Claus C. Hilgetag
<span title="2021-07-24">2021</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/oml24fsyizfuhn3rn5np75ubdi" style="color: black;">Neural Networks</a> </i> &nbsp;
Biological neuronal networks (BNNs) are a source of inspiration and analogy making for researchers that focus on artificial neuronal networks (ANNs).  ...  Moreover, neuroscientists increasingly use ANNs as a model for the brain. Despite certain similarities between these two types of networks, important differences can be discerned.  ...  Working memory is a key cognitive capacity of biological agents, extensively studied in cognitive psychology and neuroscience Conway et al. (2003) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neunet.2021.07.011">doi:10.1016/j.neunet.2021.07.011</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34391175">pmid:34391175</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yvckojv6qvha3ehwcgvbinke7m">fatcat:yvckojv6qvha3ehwcgvbinke7m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210725070025/https://pdf.sciencedirectassets.com/271125/AIP/1-s2.0-S0893608021002744/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEB8aCXVzLWVhc3QtMSJHMEUCIQD2nQOgX8kUAb395MgcBuRv86%2B4IaL1qG6rX7rQAlBYogIgPFjsEaWtePllqbvNbLVttf8RNbdyjJw%2Fc8S2J%2FmJTKUq%2BgMIJxAEGgwwNTkwMDM1NDY4NjUiDK4%2BQzxHxTR2XrF8iyrXA7XwdjBQ45wmc3436iFHSxx%2FumdS65VJo9xvl1x0dajCELF2AWvd1ZSG2pJ5BS4FdZLsnmizueZSKlEHRFHQhhbaYmNibhKiXiuOjaWAwcFjLPQhZzdriQFGCO2JBkzM0lMJJarcKM4Iina0n9inVx1tSYQqamAry75FC1hpbcBfx0Ln7MSKSFqX%2FRYGzvMOVdIwBSZNq%2BOU%2FO6A2U%2FZDet8S%2Fa9ih6XOZ7VAiGI5QWqRkP0lckLspZq56g%2BfxBKbwcW7dmGBLdMazPF1avgGuVjUJgphV5Op2fDjM0BoT0OuttfV3g6zOZQIYGVaKmhoboE3jg1g8FRON6YQyuOvALUsqRp5C%2B9%2FPGltXU5I0ymNw94vNcReVAyduCL90Ejsu7pVAN95T0KOoNmQZZ4aTliI5KDpq3x4EvexXe%2FTL2nKQFYS2m%2F13%2F1sz0EaPfpJFUG0jJYfUcvR3CwhbU1bW0JrPQsXfCQwsS3Bv%2BbI3DPNG52Px%2BHh8L8ZzIECyZdGQOhr1z3nZrnkHr5%2BvE7CTmtIcmQvoiQNVXswk%2BolMqqEK74f6f7xlRvXbapQKpyzn4eoJEVb3OUDo5l2bLM9tl2ohjsZGMrGuHBKrxrIv5zlxkZu1tmqTDng%2FSHBjqlAU%2FIr0%2BCierosQX71u%2B8c64NVlf0aswQUgsRFa944Qu%2FoLO0LfnFwTXudX6P%2BI9sLdXOL6tItfiiCawc34jw64Y4GL6fcCVsORjFBkCohjU7a2aZtIAVoLr652dfDsvTjmiG2m4OHa2txxl5MhG5dLkdZbfV9gJNKV21OgKEP9dD6ZjQK%2F2d66KtWoJPqt7%2BdElucr4ERqsvvQvEYT2SfkNXuOruhg%3D%3D&amp;X-Amz-Algorithm=AWS4-HMAC-SHA256&amp;X-Amz-Date=20210725T070020Z&amp;X-Amz-SignedHeaders=host&amp;X-Amz-Expires=300&amp;X-Amz-Credential=ASIAQ3PHCVTY5MQWWSPU%2F20210725%2Fus-east-1%2Fs3%2Faws4_request&amp;X-Amz-Signature=e5505a846526f69bb5f59c8d93692a6587c581a2f2653b5676f633c86c4a0f14&amp;hash=6f6e917fa60b9dd74ce6be6426a3c11ae11110a12b9f4837c64936edbc6c6969&amp;host=68042c943591013ac2b2430a89b270f6af2c76d8dfd086a07176afe7c76c2c61&amp;pii=S0893608021002744&amp;tid=spdf-35df19a3-8163-484d-a275-3cad772859e0&amp;sid=e6f8525b513e4149983b14d7e1b6ae9c76d3gxrqa&amp;type=client" 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/ac/0b/ac0bbd5cab53a646dd42bf7b905bc6ea724aa0e2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.neunet.2021.07.011"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a>

Deep neural networks in psychiatry

Daniel Durstewitz, Georgia Koppe, Andreas Meyer-Lindenberg
<span title="2019-02-15">2019</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ywuy2l3c7ngernsmmsbttqvzna" style="color: black;">Molecular Psychiatry</a> </i> &nbsp;
Here we will first give an overview of machine learning methods, with a focus on deep and recurrent neural networks, their relation to statistics, and the core principles behind them.  ...  We will then discuss and review directions along which (deep) neural networks can be, or already have been, applied in the context of psychiatry, and will try to delineate their future potential in this  ...  for the first unit, plus some bias term w 0i .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1038/s41380-019-0365-9">doi:10.1038/s41380-019-0365-9</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/30770893">pmid:30770893</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4azz2evu4jdszhggq64yl7qp6i">fatcat:4azz2evu4jdszhggq64yl7qp6i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200315110403/https://www.nature.com/articles/s41380-019-0365-9.pdf?error=cookies_not_supported&amp;code=dd4e93ff-3868-407a-8fe5-47930b0ac092" 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/f7/0f/f70f02bfab381f8292406103c96f2a67b1211c95.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1038/s41380-019-0365-9"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Understanding More about Human and Machine Attention in Deep Neural Networks [article]

Qiuxia Lai, Salman Khan, Yongwei Nie, Jianbing Shen, Hanqiu Sun, Ling Shao
<span title="2020-07-06">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In view of these conflicting evidence, here we make a systematic study on using artificial attention and human attention in neural network design.  ...  Understanding the relation between human and machine attention is important for interpreting and designing neural networks.  ...  for designing neural attetion in deep neural networks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.08764v3">arXiv:1906.08764v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/en74dsgmlze6pfnh46wnojavce">fatcat:en74dsgmlze6pfnh46wnojavce</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710052437/https://arxiv.org/pdf/1906.08764v3.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/af/45/af450f783f1cfaddfd59f127b2d5b8624a63dc77.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.08764v3" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 8,170 results