Predicting Structured Data

By David S. Touretzky, John E. Moody, Stephen Jose Hanson, J. Cowan, Gökhan H. Bakir, Thomas Hofmann, Bernhard Schölkopf, Alex Smola, B. Taskar, Shravan Vishwanathan and 4 more. 2008

How researchers see this paper

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

Citations in the corpus

Order Matters: Sequence to sequence for sets (2015, neutral): “Unlike traditional structured prediction algorithms (Bakir et al., 2007), our approach relies on the chain rule to serialize output random variables through the strong capabilities of LSTM networks to model long-term correlation.”
Kernel methods in machine learning (2007, neutral): “[9], Cristianini and Shawe-Taylor [37], Herbrich [64], Joachims [77], Schölkopf and Smola [118], Schölkopf [121] and Shawe-Taylor and Cristianini [123] for further examples and details.”
Recurrent Pixel Embedding for Instance Grouping (2017, background): “Pixel-level labeling tasks fall into the category of structured output prediction [4], where the model outputs a structured object (e.”
Convex Learning of Multiple Tasks and their Structure (2015, background): “[1] and references therein), with connections to structured learning [6, 34].”
Soft-DTW: a Differentiable Loss Function for Time-Series (2017, background): “This task is noticeably more difﬁcult when the output objects have a structure, i.e. when they are not vectors (Bakir et al., 2007).”
Hybrid Markov Logic Networks (2008, background): “This problem has received much attention in recent years, and many approaches have been proposed (Bakir et al. 2007; Getoor & Taskar 2007).”
Non Maximal Suppression in Cascaded Ranking Models (2013, background): “This approach was recently extended to additionally incorporate structured output losses [12, 13, 1, 2, 14], and it is this approach that the present work extends.”
Hierarchical Convolutional Deep Learning in Computer Vision (2013, background): “The problem of simultaneously predicting multiple, correlated variables has received a great deal of recent attention [3].”
Online Learning: A Comprehensive Survey (2018, background): “It can be viewed as a special type of supervised learning, known as structured prediction or structured (output) learning [299], where the goal is to predict structured objects (e.”
Predictive Markers for AD in a Multi-Modality Framework: An Analysis of MCI Progression in the ADNI Population (2010, unknown): “See Bakir et al. (2007) for details.”
Memristors for Energy‐Efficient New Computing Paradigms (2016, background): “[ 64 ] The back-propagation is an error correction algorithm that is most widely deployed in various recognition problems.”