Results 51 to 60 of about 3,629,477 (294)

Incremental Sparse Bayesian Ordinal Regression [PDF]

, 2018
Ordinal Regression (OR) aims to model the ordering information between different data categories, which is a crucial topic in multi-label learning. An important class of approaches to OR models the problem as a linear combination of basis functions that ...
de Rijke, Maarten, Li, Chang
core   +7 more sources

Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging [PDF]

, 2016
Environmental audio tagging aims to predict only the presence or absence of certain acoustic events in the interested acoustic scene. In this paper we make contributions to audio tagging in two parts, respectively, acoustic modeling and feature learning.
Foster, Peter, Huang, Qiang, Jackson, Philip J. B., Plumbley, Mark D., Sigtia, Siddharth, Wang, Wenwu, Xu, Yong   +6 more
core   +3 more sources

Variable Selection Using Deep Variational Information Bottleneck with Drop-Out-One Loss

Applied Sciences, 2023
The information bottleneck (IB) model aims to find the optimal representations of input variables with respect to the response variable. While it has been widely used in the machine-learning community, research from the perspective of the information ...
Junlong Pan, Weifu Li, Liyuan Liu, Kang Jia, Tong Liu, Fen Chen   +5 more
doaj   +1 more source

Information Bottleneck Approach to Predictive Inference

Entropy, 2014
This paper synthesizes a recent line of work on automated predictive model making inspired by Rate-Distortion theory, in particular by the Information Bottleneck method. Predictive inference is interpreted as a strategy for efficient communication.
Susanne Still
doaj   +1 more source

Sublinear information bottleneck based two-stage deep learning approach to genealogy layout recognition

Frontiers in Neuroscience, 2023
As an important part of human cultural heritage, the recognition of genealogy layout is of great significance for genealogy research and preservation.
Jianing You, Qing Wang
doaj   +1 more source

Variational Information Bottleneck for Unsupervised Clustering: Deep Gaussian Mixture Embedding

Entropy, 2020
In this paper, we develop an unsupervised generative clustering framework that combines the variational information bottleneck and the Gaussian mixture model.
Yiğit Uğur, George Arvanitakis, Abdellatif Zaidi   +2 more
doaj   +1 more source

Throughput bottleneck detection in manufacturing: a systematic review of the literature on methods and operationalization modes

Production and Manufacturing Research: An Open Access Journal, 2023
Throughput is an important parameter to evaluate production system performance. It is typically constrained by one or more resources referred to as ‘throughput bottlenecks’.
Anders Skoogh, Matthias Thürer, Mukund Subramaniyan, Andrea Matta, Christoph Roser   +4 more
doaj   +1 more source

The Effect of Evidence Transfer on Latent Feature Relevance for Clustering

Informatics, 2019
Evidence transfer for clustering is a deep learning method that manipulates the latent representations of an autoencoder according to external categorical evidence with the effect of improving a clustering outcome.
Athanasios Davvetas, Iraklis A. Klampanos, Spiros Skiadopoulos, Vangelis Karkaletsis   +3 more
doaj   +1 more source

The color of smiling: computational synaesthesia of facial expressions [PDF]

, 2015
This note gives a preliminary account of the transcoding or rechanneling problem between different stimuli as it is of interest for the natural interaction or affective computing fields. By the consideration of a simple example, namely the color response
C Spence, G Chechik, G Elidan, GL Collier, HJ Suk, J Broekens, J Vitale, J Ward, JA Russell, JA Russell, KP Murphy, L Pessoa, P Ekman, P Valdez, T Cover, XP Gao   +15 more
core   +2 more sources

An Information-Theoretic Discussion of Convolutional Bottleneck Features for Robust Speech Recognition

Iranian Journal of Electrical and Electronic Engineering, 2021
Convolutional Neural Networks (CNNs) have been shown their performance in speech recognition systems for extracting features, and also acoustic modeling.
B. Nasersharif, N. Naderi
doaj