Confidence estimation method for regression neural networks

The performances of deep neural networks (DNNs) crucially rely on the quality of labeling. In some situations, labels are easily corrupted, and therefore some labels become noisy labels. Thus, designing algorithms that deal with noisy labels is of great importance for learning robust DNNs. However, it is difficult to distinguish between clean labels and noisy labels, which becomes the bottleneck of many methods. To address the problem, this paper proposes a novel method named Label Distribution based Confidence Estimation (LDCE). LDCE estimates the confidence of the observed labels based on label distribution. Then, the boundary between clean labels and noisy labels becomes clear according to confidence scores. To verify the effectiveness of the method, LDCE is combined with the existing learning algorithm to train robust DNNs. Experiments on both synthetic and real-world datasets substantiate the superiority of the proposed algorithm against state-of-the-art methods.

Download Full-text

Estimation Method of Motion Fields from Images by Model Inclusive Learning of Neural Networks

Artificial Neural Networks – ICANN 2009 - Lecture Notes in Computer Science ◽

10.1007/978-3-642-04277-5_68 ◽

2009 ◽

pp. 673-683 ◽

Cited By ~ 6

Author(s):

Yasuaki Kuroe ◽

Hajimu Kawakami

Keyword(s):

Neural Networks ◽

Estimation Method ◽

Inclusive Learning

Download Full-text

Bi-directional Lattice Recurrent Neural Networks for Confidence Estimation

ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ◽

10.1109/icassp.2019.8683488 ◽

2019 ◽

Cited By ~ 2

Author(s):

Q. Li ◽

P. M. Ness ◽

A. Ragni ◽

M. J. F. Gales

Keyword(s):

Neural Networks ◽

Recurrent Neural Networks ◽

Confidence Estimation

Download Full-text

Multiple Network Fusion with Low-Rank Representation for Image-Based Age Estimation

Applied Sciences ◽

10.3390/app8091601 ◽

2018 ◽

Vol 8 (9) ◽

pp. 1601

Author(s):

Chaoqun Hong ◽

Zhiqiang Zeng ◽

Xiaodong Wang ◽

Weiwei Zhuang

Keyword(s):

Neural Networks ◽

Age Estimation ◽

Feature Fusion ◽

Estimation Method ◽

Feature Space ◽

Image Features ◽

Low Rank ◽

Face Images ◽

Low Rank Representation ◽

Multiple Network

Image-based age estimation is a challenging task since there are ambiguities between the apparent age of face images and the actual ages of people. Therefore, data-driven methods are popular. To improve data utilization and estimation performance, we propose an image-based age estimation method. Theoretically speaking, the key idea of the proposed method is to integrate multi-modal features of face images. In order to achieve it, we propose a multi-modal learning framework, which is called Multiple Network Fusion with Low-Rank Representation (MNF-LRR). In this process, different deep neural network (DNN) structures, such as autoencoders, Convolutional Neural Networks (CNNs), Recursive Neural Networks (RNNs), and so on, can be used to extract semantic information of facial images. The outputs of these neural networks are then represented in a low-rank feature space. In this way, feature fusion is obtained in this space, and robust multi-modal image features can be computed. An experimental evaluation is conducted on two challenging face datasets for image-based age estimation extracted from the Internet Move Database (IMDB) and Wikipedia (WIKI). The results show the effectiveness of the proposed MNF-LRR.

Download Full-text

Fast battery capacity estimation using convolutional neural networks

Transactions of the Institute of Measurement and Control ◽

10.1177/0142331220966425 ◽

2020 ◽

pp. 014233122096642 ◽

Cited By ~ 1

Author(s):

Yihuan Li ◽

Kang Li ◽

Xuan Liu ◽

Li Zhang

Keyword(s):

Machine Learning ◽

Neural Networks ◽

Smart Grids ◽

Estimation Method ◽

Lithium Ion ◽

Accurate Estimation ◽

Capacity Estimation ◽

Starting Point ◽

Battery Capacity ◽

Mean Square Errors

Lithium-ion batteries have been widely used in electric vehicles, smart grids and many other applications as energy storage devices, for which the aging assessment is crucial to guarantee their safe and reliable operation. The battery capacity is a popular indicator for assessing the battery aging, however, its accurate estimation is challenging due to a range of time-varying situation-dependent internal and external factors. Traditional simplified models and machine learning tools are difficult to capture these characteristics. As a class of deep neural networks, the convolutional neural network (CNN) is powerful to capture hidden information from a huge amount of input data, making it an ideal tool for battery capacity estimation. This paper proposes a CNN-based battery capacity estimation method, which can accurately estimate the battery capacity using limited available measurements, without resorting to other offline information. Further, the proposed method only requires partial charging segment of voltage, current and temperature curves, making it possible to achieve fast online health monitoring. The partial charging curves have a fixed length of 225 consecutive points and a flexible starting point, thereby short-term charging data of the battery charged from any initial state-of-charge can be used to produce accurate capacity estimation. To employ CNN for capacity estimation using partial charging curves is however not trivial, this paper presents a comprehensive approach covering time series-to-image transformation, data segmentation, and CNN configuration. The CNN-based method is applied to two battery degradation datasets and achieves root mean square errors (RMSEs) of less than 0.0279 Ah (2.54%) and 0.0217 Ah (2.93% ), respectively, outperforming existing machine learning methods.

Download Full-text