Pattern recognition

By Sergios Theodoridis, Konstantinos Koutroumbas. 1974

This conference brings together scientists in the field of Pattern Recognition from all over the world. The program for this conference will cover all aspects of theoretical and applied Pattern Recognition. Moreover, a number of speakers is invited to give a survey of some key problems, including their ideas about trends and future developments.

Subfields: Evaluation & Benchmarks

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

Towards the Science of Security and Privacy in Machine Learning (2016, background): “Readers interested in a broad survey of ML are well served by many books covering this rich topic [3], [15], [16].”
Defeating Image Obfuscation with Deep Learning (2016, background): “The learning rate and momentum control the magnitude of updates to the neural-network parameters during the training [4,40].”
Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples (2016, methodology): “For each class k of the machine learning task, a binary Support Vector Machine classiﬁer f k is trained with samples of class k labeled as positive and samples from other classes labeled as negative [8].”
Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations (2017, methodology): “…from the decision boundary, they can be uniformatively small and do not always capture the idea of salience (see discussion and alternatives proposed in [Shrikumar et al., 2016; Bach et al., 2015; Montavon et al., 2017; Sundararajan et al., 2016; Shrikumar et al., 2017; Fong and Vedaldi, 2017]).”
Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity (2019, methodology): “UGRAPHEMB even outperforms HED [Fischer et al., 2015], a state-of-the-art approximate GED computation algorithm, under most settings, further confirming its strong ability to generate proximity-preserving graph embeddings by learning from a specific graph proximity metric, which is GED in this case.”
SoK: Security and Privacy in Machine Learning (2018, background): “Readers interested in surveys of ML are well served by many books covering this rich topic [5], [16], [17].”
From Parity to Preference-based Notions of Fairness in Classification (2017, methodology): “To overcome this difficulty, we minimize instead a convex loss function `θ(x, y), which is classifier dependent [6], and approximate the group benefits using a ramp (convex) function r(x) = max(0, x), i.”
Crafting adversarial input sequences for recurrent neural networks (2016, background): “In such settings, the output data nature characterizes varying problems like classification [12], [13], [14], pattern recognition [15], or regression [16].”
Deep Learning for Health Informatics (2017, background): “For more general background information related to the theory of machine learning, the reader can refer to the works in [23]–[25] where common training problems, such as overfitting, model interpretation and generalization, are explained in detail.”
Combining multiple clusterings using evidence accumulation (2005, background): “A large number of clustering algorithms exist [7], [8], [9], [10], [11], yet no single algorithm is able to identify all sorts of cluster shapes and structures that are encountered in practice.”
Deconstructing multivariate decoding for the study of brain function (2017, methodology): “In this case, the Bayes-optimal classifier is the Fisher linear discriminant (Bishop, 2006).”
Feature extraction and classification of Chilean wines (2006, methodology): “The PNN uses Parzen (or Parzen-like) probability distribution function estimators that approach the true underlying parent density (Theodoridis & Koutroumbas, 1999).”
SHREC 2007 3 D Shape Retrieval Contest (2006, background): “Having a common understanding on 3D shape retrieval would help users to orient themselves to select the retrieved technique most suitable for their own specific needs.”
Optimized Cost per Click in Taobao Display Advertising (2017, methodology): “The results show that the performance of daily models conducted by MLR algorithm are fairly stable.”