分支进入大脑。
Branching into brains.
机构信息
Department of Biology, Stanford University, Stanford, United States.
Neurocure Cluster of Excellence, Humboldt University, Berlin, Germany.
出版信息
Elife. 2017 Dec 5;6:e33066. doi: 10.7554/eLife.33066.
Abstract
What can artificial intelligence learn from neuroscience, and vice versa?
摘要
人工智能可以从神经科学中学到什么，反之亦然？
相似文献
1
Branching into brains.分支进入大脑。
Elife. 2017 Dec 5;6:e33066. doi: 10.7554/eLife.33066.
2
Towards deep learning with segregated dendrites.走向具有分离树突的深度学习。
Elife. 2017 Dec 5;6:e22901. doi: 10.7554/eLife.22901.
3
Using neuroscience to develop artificial intelligence.利用神经科学开发人工智能。
Science. 2019 Feb 15;363(6428):692-693. doi: 10.1126/science.aau6595.
4
Neuroscience-Inspired Artificial Intelligence.神经科学启发的人工智能。
Neuron. 2017 Jul 19;95(2):245-258. doi: 10.1016/j.neuron.2017.06.011.
5
Forms of explanation and understanding for neuroscience and artificial intelligence.神经科学和人工智能的解释和理解形式。
J Neurophysiol. 2021 Dec 1;126(6):1860-1874. doi: 10.1152/jn.00195.2021. Epub 2021 Oct 13.
6
Deep Learning and Computational Neuroscience.深度学习与计算神经科学
Neuroinformatics. 2018 Jan;16(1):1-2. doi: 10.1007/s12021-018-9360-6.
7
If deep learning is the answer, what is the question?如果深度学习是答案，那么问题是什么？
Nat Rev Neurosci. 2021 Jan;22(1):55-67. doi: 10.1038/s41583-020-00395-8. Epub 2020 Nov 16.
8
Infrastructural intelligence: Contemporary entanglements between neuroscience and AI.基础设施智能：神经科学与人工智能之间的当代纠葛
Prog Brain Res. 2017;233:101-128. doi: 10.1016/bs.pbr.2017.06.004. Epub 2017 Jul 31.
9
[Deep Learning and AlphaGo].[深度学习与阿尔法围棋]
Brain Nerve. 2019 Jul;71(7):681-694. doi: 10.11477/mf.1416201340.
10
[Brain and Artificial Intelligence].[大脑与人工智能]
Brain Nerve. 2019 Dec;71(12):1349-1355. doi: 10.11477/mf.1416201454.
引用本文的文献
1
Learning on tree architectures outperforms a convolutional feedforward network.基于树结构的学习优于卷积前馈网络。
Sci Rep. 2023 Jan 30;13(1):962. doi: 10.1038/s41598-023-27986-6.
2
Efficient dendritic learning as an alternative to synaptic plasticity hypothesis.高效的树突学习作为突触可塑性假说的替代方案。
Sci Rep. 2022 Apr 28;12(1):6571. doi: 10.1038/s41598-022-10466-8.
3
Dendritic normalisation improves learning in sparsely connected artificial neural networks.树突正常化可改善稀疏连接人工神经网络的学习能力。
PLoS Comput Biol. 2021 Aug 9;17(8):e1009202. doi: 10.1371/journal.pcbi.1009202. eCollection 2021 Aug.
4
Deep learning networks reflect cytoarchitectonic features used in brain mapping.深度学习网络反映了用于脑图谱绘制的细胞构筑特征。
Sci Rep. 2020 Dec 16;10(1):22039. doi: 10.1038/s41598-020-78638-y.
本文引用的文献
1
Towards deep learning with segregated dendrites.走向具有分离树突的深度学习。
Elife. 2017 Dec 5;6:e22901. doi: 10.7554/eLife.22901.
2
Mastering the game of Go without human knowledge.无需人类知识即可掌握围棋游戏。
Nature. 2017 Oct 18;550(7676):354-359. doi: 10.1038/nature24270.
3
Spiking neurons can discover predictive features by aggregate-label learning.尖峰神经元可以通过聚合标签学习发现预测特征。
Science. 2016 Mar 4;351(6277):aab4113. doi: 10.1126/science.aab4113.
4
Deep learning.深度学习。
Nature. 2015 May 28;521(7553):436-44. doi: 10.1038/nature14539.
5
A cellular mechanism for cortical associations: an organizing principle for the cerebral cortex.一种皮质关联的细胞机制：大脑皮层的组织原则。
Trends Neurosci. 2013 Mar;36(3):141-51. doi: 10.1016/j.tins.2012.11.006. Epub 2012 Dec 25.
6
Spatio-temporal credit assignment in neuronal population learning.神经元群体学习中的时空信用分配。
PLoS Comput Biol. 2011 Jun;7(6):e1002092. doi: 10.1371/journal.pcbi.1002092. Epub 2011 Jun 30.
7
Layer I of primary sensory neocortex: where top-down converges upon bottom-up.初级感觉新皮层的第I层：自上而下与自下而上的汇聚之处。
Behav Brain Res. 1995 Nov;71(1-2):163-70. doi: 10.1016/0166-4328(95)00032-1.
Zotero 插件