Inductive Learning in Symbolic Domains Using Structure-Driven Recurrent Neural Networks
By Andreas Küchler, Christoph Goller. 1996
Subfields: Model Architectures
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Model Architectures
- Regina Barzilay
- Tao Lei
- Tommi S. Jaakkola
- Phil Blunsom
- Edward Grefenstette
- Yoshua Bengio
- Nal Kalchbrenner
- Kyunghyun Cho
Citations in the corpus
- A Convolutional Neural Network for Modelling Sentences (2014, methodology): “A model that adopts a more general structure provided by an external parse tree is the Recursive Neural Network (RecNN) (Pollack, 1990; K¨uchler and Goller, 1996; Socher et al., 2011; Hermann and Blunsom, 2013).”
- The Graph Neural Network Model (2009, neutral): “Recursive neural networks have been applied to several problems including logical term classification [25], chemical compound classification [26], logo recognition [2], [27], web page scoring [28], and face localization [29].”
- Unsupervised Object Keypoint Learning using Local Spatial Predictability (2020, methodology): “) are taken from Kulkarni et al. (2019) and for SimPLE, PPO, and Rainbow from (Kaiser et al.”
- A Comparison between Recursive Neural Networks and Graph Neural Networks (2006, methodology): “Such techniques have been applied successfully on several problems as logical term classification [20], chemical compound classification [21], logo recognition [2], [22], Web page scoring [23], and face localization [24].”
- Processing directed acyclic graphs with recursive neural networks (2001, background): “Remark 1: Learning in recursive neural networks with shared weights can be carried out via standard backpropagation through structure [ 3 ], [23] so as in standard (not with shared weights) architectures.”
- Molding CNNs for text: non-linear, non-consecutive convolutions (2015, background): “…differences, ranging from recurrent neural networks (Mikolov et al., 2010; Kalchbrenner and Blunsom, 2013) to recursive models (Pollack, 1990; Küchler and Goller, 1996), and including convolutional neural nets (Collobert and Weston, 2008; Collobert et al., 2011; Yih et al., 2014; Shen et…”