Advances in Neural Information Processing Systems 25

By Shay B. Cohen, Michael Collins. 2012

208 citations recorded by the source corpus.

How researchers see this paper

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

In Evaluation & Benchmarks

Citations in the corpus

Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin (2015, positive): “In contrast to previous large-scale training approaches that use parameter servers and asynchronous updates [18, 10], we use synchronous SGD, which is easier to debug while testing new ideas, and also converges faster for the same degree of data parallelism.”
Optimization Methods for Large-Scale Machine Learning (2016, neutral): “…. . . 25 4.3 SG for General Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 4.4 Work Complexity for Large-Scale Learning . . . . . . . . . . . . . . . . . . . . . . . 33 4.5 Commentary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36”
Learning atoms for materials discovery (2018, background): “Explicitly, the model is written as h = Relu(W · l + b), [6] Eformation = w · h + e, [7] where W and b are weights and bias between the input layer and the hidden layer, w and e are weights and bias between the hidden layer and output layer.”
Discriminative Transfer Learning with Tree-based Priors (2013, background): “We structure the prior so that related classes share the same prior.”
Hierarchical Convolutional Deep Learning in Computer Vision (2013, background): “DBMs provide a powerful generative framework for high level reasoning of object classes [110] and for modelling complex object part relationships in natural images [32].”
Ernest: Efficient Performance Prediction for Large-Scale Advanced Analytics (2016, background): “…decade we have seen a rapid growth of large-scale advanced analytics that implement complex algorithms in areas like distributed natural language processing [24, 74], deep learning for image recognition [34], genome analysis [72, 61], astronomy [17] and particle accelerator data processing [19].”
Deep forest (2017, background): “For example, even when several authors all use convolutional neural networks [LeCun et al., 1998; Krizhenvsky et al., 2012; Simonyan and Zisserman, 2014], they are actually using different learning models due to the many different options such as the convolutional layer structures.”
DeepLabCut: markerless pose estimation of user-defined body parts with deep learning (2018, background): “Training predictors based on features from deep neural networks also falls in this category [23, 24].”
Gradient Coding (2016, background): “The problem is that sometimes worker nodes can be stragglers (Li et al., 2014; Ho et al., 2013; Dean et al., 2012) i.e. delay signiﬁcantly in computing and communicating gradient vectors to the master.”
Deep learning with COTS HPC systems (2013, methodology): “Each of these approaches comes with its own set of engineering complications, yet significant progress has been made along each axis (Raina et al., 2009; Krizhevsky et al., 2012; Ciresan et al., 2012; Uetz & Behnke, 2009; Dean et al., 2012).”
An exact mapping between the Variational Renormalization Group and Deep Learning (2014, background): “Deep learning uses multiple layers of representation to learn descriptive features directly from training data [1, 2] and has been successfully utilized, often achieving record breaking results, in difficult machine learning tasks including object labeling [3], speech recognition [4], and natural la”