Artificial astrocytes improve neural network performance.
Artificial astrocytes improve neural network performance.
复制标题
DOI：
10.1371/journal.pone.0019109
复制
发表时间：
2011-04-19
期刊：
影响因子：
3.7
通讯作者：
Araque A
中科院分区：
文献类型：
--
作者：
Porto-Pazos AB;Veiguela N;Mesejo P;Navarrete M;Alvarellos A;Ibáñez O;Pazos A;Araque A
令人信服的证据表明星形胶质细胞和神经元之间存在双向通讯。星形胶质细胞是一种传统上被认为是被动支持细胞的神经胶质细胞，最近被证明积极参与突触信息的处理和调节，这表明大脑功能源于神经元-神经胶质网络的活动。然而，星形胶质细胞对神经网络功能的实际影响在很大程度上尚不清楚，其在人工智能中的应用也尚未经过测试。我们研究了人工星形胶质细胞对人工神经网络性能的影响，人工星形胶质细胞具有星形胶质细胞-神经元通信所涉及的生物学定义的特性。使用联结主义系统和进化算法，我们比较了人工神经网络（NN）和人工神经元神经胶质网络（NGN）解决分类问题的性能。我们表明 NGN 的成功程度优于 NN。对具有不同神经元数量或不同架构的 NN 性能的分析表明，NGN 的影响不能归因于网络元素数量的增加，而是特别归因于星形胶质细胞。此外，NGN 与 NN 的相对功效随着网络复杂性的增加而增加。这些结果表明人工星形胶质细胞改善了神经网络的性能，并建立了人工神经元-神经胶质网络的概念，它代表了人工智能中的一个新概念，对计算科学以及对大脑功能的理解具有影响。
Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function.
登录
查看更多内容
影响因子：
2.9
作者：
Rabuñal, JR;Dorado, J;Rivero, D
通讯作者：
Rivero, D
DOI：
10.1093/jee/39.2.269
发表时间：
1945-01-01
期刊：
BIOMETRICS BULLETIN
影响因子：
--
作者：
WILCOXON, F
通讯作者：
WILCOXON, F
影响因子：
56.9
作者：
Perea, Gertrudis;Araque, Alfonso
通讯作者：
Araque, Alfonso
影响因子：
25
作者：
Grosche, J;Matyash, V;Kettenmann, H
通讯作者：
Kettenmann, H
DOI：
10.1073/pnas.79.8.2554
发表时间：
1982-01-01
期刊：
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA-BIOLOGICAL SCIENCES
影响因子：
--
作者：
HOPFIELD, JJ
通讯作者：
HOPFIELD, JJ