Results 41 to 50 of about 25,867,085 (318)

Clustering Analysis of Unlabeled Data and Weak-Label Detection Analysis Method Integrating Soft Computing Technology

IEEE Access
With the continuous improvement of digitization, the processing and analysis of massive data has become one of the hot issues. Soft computing technology, as an emerging machine intelligence technology, performs well in handling complex uncertainty ...
Chunhua Liang
doaj   +1 more source

A Threshold-Control Generative Adversarial Network Method for Intelligent Fault Diagnosis

Complex System Modeling and Simulation, 2021
Fault diagnosis plays the increasingly vital role to guarantee the machine reliability in the industrial enterprise. Among all the solutions, deep learning (DL) methods have achieved more popularity for their feature extraction ability from the raw ...
Xinyu Li, Sican Cao, Liang Gao, Long Wen
doaj   +1 more source

Audio Event Detection using Weakly Labeled Data

, 2016
Acoustic event detection is essential for content analysis and description of multimedia recordings. The majority of current literature on the topic learns the detectors through fully-supervised techniques employing strongly labeled data.
Gencoglu O., J. F., Kons Z., Kumar A., Mandel M. I., Pancoast S., Pikrakis A., Rumelhart D. E., Stowell D., Wang F., Wang J., Werbos P. J., Zhou Z.-H.   +12 more
core   +1 more source

Multi-Modal Dataset of Human Activities of Daily Living with Ambient Audio, Vibration, and Environmental Data

Data
The detection of human activities is an important step in automated systems to understand the context of given situations. It can be useful for applications like healthcare monitoring, smart homes, and energy management systems for buildings.
Thomas Pfitzinger, Marcel Koch, Fabian Schlenke, Hendrik Wöhrle   +3 more
doaj   +1 more source

Gradient Agreement Hinders the Memorization of Noisy Labels

Applied Sciences, 2023
The performance of deep neural networks (DNNs) critically relies on high-quality annotations, while training DNNs with noisy labels remains challenging owing to their incredible capacity to memorize the entire training set.
Shaotian Yan, Xiang Tian, Rongxin Jiang, Yaowu Chen   +3 more
doaj   +1 more source

MdpCaps-Csl for SAR Image Target Recognition With Limited Labeled Training Data

IEEE Access, 2020
Although convolutional neural networks (CNN) have shown excellent performance in many image recognition tasks, it commonly requires a lot of labeled data, and the recognition effect is frequently unsatisfied due to the limited labeled training data.
Yuchao Hou, Ting Xu, Hongping Hu, Peng Wang, Hongxin Xue, Yanping Bai   +5 more
doaj   +1 more source

Handwriting Recognition of Historical Documents with few labeled data

, 2018
Historical documents present many challenges for offline handwriting recognition systems, among them, the segmentation and labeling steps. Carefully annotated textlines are needed to train an HTR system.
Chammas, Edgard, Likforman-Sulem, Laurence, Mokbel, Chafic   +2 more
core   +1 more source

Using Anchors to Estimate Clinical State without Labeled Data. [PDF]

AMIA Annu Symp Proc, 2014
Halpern Y, Choi Y, Horng S, Sontag D.
europepmc   +2 more sources

Learning From Noisy Singly-labeled Data [PDF]

, 2018
Supervised learning depends on annotated examples, which are taken to be the \emph{ground truth}. But these labels often come from noisy crowdsourcing platforms, like Amazon Mechanical Turk. Practitioners typically collect multiple labels per example and
Anandkumar, Anima, Khetan, Ashish, Lipton, Zachary C.   +2 more
core   +1 more source

Learning From Labeled And Unlabeled Data: An Empirical Study Across Techniques And Domains

, 2011
There has been increased interest in devising learning techniques that combine unlabeled data with labeled data ? i.e. semi-supervised learning. However, to the best of our knowledge, no study has been performed across various techniques and different ...
Chawla, N. V., Karakoulas, Grigoris
core   +1 more source