Neuro-symbolic computing with spiking neural networks

被引:2
作者
Dold, Dominik [1 ]
Soler Garrido, Josep [2 ]
Chian, Victor Caceres [3 ]
Hildebrandt, Marcel [3 ]
Runkler, Thomas [3 ]
机构
[1] European Space Agcy ESTEC, Adv Concepts Team, Noordwijk, Netherlands
[2] Joint Res Ctr JRC, European Commiss, Seville, Spain
[3] Siemens AG Technol, Munich, Germany
来源
PROCEEDINGS OF INTERNATIONAL CONFERENCE ON NEUROMORPHIC SYSTEMS 2022, ICONS 2022 | 2022年
关键词
graph embedding; relational learning; symbolic AI; spiking neural network; graph neural network; neuromorphic computing;
D O I
10.1145/3546790.3546824
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Knowledge graphs are an expressive and widely used data structure due to their ability to integrate data from different domains in a sensible and machine-readable way. Thus, they can be used to model a variety of systems such as molecules and social networks. However, it still remains an open question how symbolic reasoning could be realized in spiking systems and, therefore, how spiking neural networks could be applied to such graph data. Here, we extend previous work on spike-based graph algorithms by demonstrating how symbolic and multi-relational information can be encoded using spiking neurons, allowing reasoning over symbolic structures like knowledge graphs with spiking neural networks. The introduced framework is enabled by combining the graph embedding paradigm and the recent progress in training spiking neural networks using error backpropagation. The presented methods are applicable to a variety of spiking neuron models and can be trained end-to-end in combination with other differentiable network architectures, which we demonstrate by implementing a spiking relational graph neural network.
引用
收藏
页数:4
相关论文
共 34 条
[1]  
Ali Abdullahi, 2019, arXiv
[2]  
[Anonymous], Proceedings of the 2008 ACM SIGMOD international conference on Management of data, SIGMOD '08
[3]   DBpedia: A nucleus for a web of open data [J].
Auer, Soeren ;
Bizer, Christian ;
Kobilarov, Georgi ;
Lehmann, Jens ;
Cyganiak, Richard ;
Ives, Zachary .
SEMANTIC WEB, PROCEEDINGS, 2007, 4825 :722-+
[4]  
Bordes A., 2013, NIPS'13, P1
[5]  
Brickley Dan., 1999, Resource description framework (rdf) schema specification
[6]  
Chian Victor Caceres, 2021, 2021 International Conference on Neuromorphic Computing (ICNC), P61, DOI 10.1109/ICNC52316.2021.9607968
[7]  
Comsa JM, 2020, INT CONF ACOUST SPEE, P8529, DOI [10.1109/icassp40776.2020.9053856, 10.1109/ICASSP40776.2020.9053856]
[8]   Biologically Plausible, Human-Scale Knowledge Representation [J].
Crawford, Eric ;
Gingerich, Matthew ;
Eliasmith, Chris .
COGNITIVE SCIENCE, 2016, 40 (04) :782-821
[9]   SpikE: spike-based embeddings for multi-relational graph data [J].
Dold, Dominik ;
Garrido, Josep Soler .
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
[10]   Relational representation learning with spike trains [J].
Dold, Dominik .
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,