Advances

By D. Watt. 1972

How researchers see this paper

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

CamemBERT: a Tasty French Language Model (2019, methodology): “…word embeddings The first neural word vector representations were noncontextualised word embeddings, most notably word2vec (Mikolov et al., 2013), GloVe (Pennington et al., 2014) and fastText (Mikolov et al., 2018), which were designed to be used as input to task-specific neural architectures.”
EARLINET correlative measurements for CALIPSO: First intercomparison results (2010, background): “Before that, the first well ‐ documented experience with lidar in space was the Lidar In ‐ space Technology Experiment (LITE) mission, an 11 day mission on the space shuttle carried out in 1994 [ McCormick et al. , 1993; Ansmann et al. , 1997].”
Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions (2018, methodology): “Early pruning approaches include Biased Weight Decay (Hanson & Pratt, 1989), Optimal Brain Damage (Cun et al., 1990), and Optimal Brain Surgeon (Hassibi & Stork, 1993).”
Deep learning for molecular generation and optimization - a review of the state of the art (2019, background): “40,42 Approaches which generate feature vectors from 3D coordinates that are invariant to translation and rotation are wavelet transform invariants, 43 solid harmonic wavelet scattering transforms, 44 and tensor ﬁeld networks.”