Pattern Recognition and Neural Networks

By Yann LeCun, Yoshua Bengio. 1995

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Residual Learning for Image Recognition (2015, background): “An early practice of training multi-layer perceptrons (MLPs) is to add a linear layer connected from the network input to the output [34, 49].”
Inductive Logic Programming: Theory and Methods (1994, background): “Classifies by considering for each layer of the network, where the input belongs to[16].”
Gene selection and classification of microarray data using random forest (2006, neutral): “• K nearest neighbor (KNN) KNN is a non-parametric classification method that predicts the sample of a test case as the majority vote among the k nearest neighbors of the test case [15,16].”
BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm (2004, methodology): “The values of the two parameters were varied systematically and their efficiency was assessed by cross-validation [ 6 ] with the whole training set.”
A Practical Approach to Microarray Data Analysis (2003, methodology): “This paradigm is used by popular classification procedures such as: logistic regression (chapter 3 in (Ripley, 1996); neural networks (chapter in (Ripley, 1996), and Chapter 11 in the present book); classification trees (Chapter 10 in the present book and (Breiman et al.”
Hermitian Polynomial for Speaker Adaptation of Connectionist Speech Recognition Systems (2013, unknown): “, [28], [29], [30]),”
Support Vector Machines for Automated Recognition of Obstructive Sleep Apnea Syndrome From ECG Recordings (2009, methodology): “SVMs introduced by Vapnik [40] are a relatively new technique for classification and regression tasks.”
Explaining Rare Events in International Relations (2001, unknown): “Ripley 1996. too short.”
Shape Matching and Object Recognition Using Shape Contexts (2002, methodology): “Extensive reviews of nearest neighbor editing methods can be found in Ripley [46] and Dasarathy [12].”
Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS (2012, background): “Haykin (1999) and Bishop (2003) also give comprehensive introductions, and Ripley (2007) gives a good introduction from a statistical point of view.”
On deep learning as a remedy for the curse of dimensionality in nonparametric regression (2019, background): “(28) The weights above can be chosen such that |aj,k| ≤ 1 ε · δ ·max{‖v1‖∞, |w1|, .”
Statistical cues for domain specific image segmentation with performance analysis (2000, background): “It is important to ensure that we have enough training data so that we do not overlearn the data, see [9].”
Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks (2002, background): “…entered into the network and an output value is generated without gaining any understanding of the inter-relationships between the variables, and therefore, providing no explanatory insight into the underlying mechanisms being modeled by the network (Anderson, 1995; Bishop, 1995; Ripley, 1996).”
Adaptive computation and machine learning (1998, background): “, as in ridge regression or weight decay in neural network training (Cherkassky and Mulier, 1998; Ripley, 1996; Bishop, 1995)) or penalizes their global smoothness properties (e.”