Networks

2007

Subfields: Network Science & Complex Systems

Citations in the corpus

Training Very Deep Networks (2015, neutral): “Experiments showed [18] that certain activation functions based on local competition [18, 19] may help to train deeper networks.”
Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules (2013, neutral): “43-45 When the data consists of points with the same format and size, such as vector of fixed length or images of fixed size, then one can use a deep stack of neural networks to process the data.”
How Powerful are Graph Neural Networks? (2018, neutral): “Not surprisingly, building blocks of GIN, e.g. sum aggregation and MLP encoding, also appeared in other models (Battaglia et al., 2016; Scarselli et al., 2009b; Duvenaud et al., 2015).”
Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015, neutral): “View-pooling layers are closely related to max-pooling layers and maxout layers [15], with the only difference in terms of implementation being the dimension their pooling operations are carried on.”
Torsional Diffusion for Molecular Conformer Generation (2022, positive): “Instead, we leverage the ability of equivariant networks based on tensor products [Thomas et al., 2018, Geiger et al., 2022] to produce pseudoscalar outputs.”
Toward an Integration of Deep Learning and Neuroscience (2016, positive): “This observation is concordant with the increasing use of pre-specialized architectures and specialized computational components in machine learning (Graves et al., 2014; Weston et al., 2014; Neelakantan et al., 2015).”
Recurrent Memory Transformer (2022, unknown): “Memory Networks (Weston et al., 2014; Sukhbaatar et al., 2015) were designed to enable reasoning by sequential attention over to the content of a memory.”
Scale-free networks are rare (2018, unknown): “We expect two of the methods, preferential attachment [42] and vertex copying [43], to generate scale-free networks, and Erdős-Rényi random graphs not to.”