Neural methods for non-standard data

By Barbara Hammer, Brijnesh J. Jain. 2004

36 citations recorded by the source corpus.

Subfields: Natural Language Processing, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Marc Brockschmidt
2. Daniel Tarlow
3. Marco Gori
4. Hendrik Blockeel
5. Richard S. Zemel
6. Werner Uwents
7. Gabriele Monfardini
8. Yujia Li

In Multimodal Learning

1. Marco Gori
2. Richard S. Zemel
3. Gabriele Monfardini
4. Franco Scarselli
5. Devi Parikh
6. Marcus Rohrbach
7. Qi Wu
8. Anton van den Hengel

Citations in the corpus

• Gated Graph Sequence Neural Networks (2015, background): “Similar ideas appear in Hammer & Jain (2004) and Bottou (2014).”
• The Graph Neural Network Model (2009, neutral): “Recursive neural networks are also related to support vector machines [30]–[32], which adopt special kernels to operate on graph structured data.”
• A Comparison between Recursive Neural Networks and Graph Neural Networks (2006, background): “More recently, new connectionist models, capable to directly elaborate graphs and trees without a preprocessing phase were proposed [10].”
• Neural networks for relational learning: an experimental comparison (2011, methodology): “In the last years, new connectionist models were proposed that are capable to take in input graphs and trees directly, embedding the relationships between nodes into the processing scheme (Hammer and Jain 2004).”