Titlebook: Artificial Neural Networks in Pattern Recognition; 7th IAPR TC3 Worksho Friedhelm Schwenker,Hazem M. Abbas,Edmondo Trentin Conference proce

Insubordinate

向宇宙

On the Harmony Search Using Quaternionsnsional spaces, non-convex functions might become too tricky to be optimized, thus requiring different representations aiming at smoother fitness landscapes. In this paper, we present a variant of the Harmony Search algorithm based on quaternions, which extend complex numbers and have been shown to

DEMUR

收養(yǎng)

Towards Effective Classification of Imbalanced Data with Convolutional Neural Networksl network classifiers fail to learn to classify such datasets correctly if class-to-class separability is poor due to a strong bias towards the majority class. In this paper we present an algorithmic solution, integrating different methods into a novel approach using a class-to-class separability sc

BUST

小卒

Comparing Incremental Learning Strategies for Convolutional Neural Networksn and object detection, being able to extract meaningful high-level invariant features. However, partly because of their complex training and tricky hyper-parameters tuning, CNNs have been scarcely studied in the context of incremental learning where data are available in consecutive batches and ret

Microaneurysm

Approximation of Graph Edit Distance by Means of a Utility Matrixf a linear sum assignment problem, the major drawback of this dissimilarity model, viz.?the exponential time complexity, has been invalidated recently. Yet, the substantial decrease of the computation time is at the expense of an approximation error. The present paper introduces a novel transformati

anchor

Learning Sequential Data with the Help of Linear Systemsical systems play an important role. These approaches are empirically assessed on two nontrivial datasets of sequences on a prediction task. Experimental results show that indeed linear dynamical systems can either directly provide a satisfactory solution, as well as they may be crucial for the success of more sophisticated nonlinear approaches.

虛假

Co-training with Credal Modelso-training, in which a classifier strengthen another one by feeding it with new labeled data. We propose several co-training strategies to exploit the potential indeterminacy of credal classifiers and test them on several UCI datasets. We then compare the best strategy to the standard co-training process to check its efficiency.

后來

Interpretable Classifiers in Precision Medicine: Feature Selection and Multi-class Categorizationextent biomarkers that characterize pairwise differences among classes, correspond to biomarkers that discriminate one class from all remaining. We compare one-against-one and one-against-all architectures of feature selecting base classifiers. They are validated for their classification performance and their stability of feature selection.