In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
According to Koestler, the notion of a bisociation denotes a connection between pieces of information from habitually separated domains or categories. In this paper, we consider a ...
Pattern mining methods for graph data have largely been restricted to ground features, such as frequent or correlated subgraphs. Kazius et al. have demonstrated the use of elaborat...
Andreas Maunz, Christoph Helma, Tobias Cramer, Ste...
Graphs are increasingly used to model a variety of loosely structured data such as biological or social networks and entityrelationships. Given this profusion of large-scale graph ...
Stephan Seufert, Srikanta J. Bedathur, Juliá...
We consider a cognitive two-way relay network which consists of two transceivers (primary users) and multiple cognitive terminals. The two transceivers transmit their data toward t...