A diversity-penalizing ensemble training method for deep learning

2015 ◽  
Author(s):  
Xiaohui Zhang ◽  
Daniel Povey ◽  
Sanjeev Khudanpur
Keyword(s):  
Deep Learning ◽  
Training Method

Errata for "Cerebro: a data system for optimized deep learning model selection"

2021 ◽  
Vol 14 (6) ◽  
pp. 863-863
Author(s):  
Supun Nakandala ◽  
Yuhao Zhang ◽  
Arun Kumar
Keyword(s):  
Deep Learning ◽  
Model Selection ◽  
Learning Model ◽  
Communication Cost ◽  
Data System ◽  
Training Method ◽  
Fine Grained ◽  
Correct Communication ◽  
Deep Learning Model

We discovered that there was an inconsistency in the communication cost formulation for the decentralized fine-grained training method in Table 2 of our paper [1]. We used Horovod as the archetype for decentralized fine-grained approaches, and its correct communication cost is higher than what we had reported. So, we amend the communication cost of decentralized fine-grained to [EQUATION]

Effective deep learning training method using blur and noise filter to detect defection in TFT-LCD PAD

2021 ◽  
Author(s):  
JaeGu Lee ◽  
Yeo Min Yoon ◽  
Seon Geol Kim ◽  
Chang Woo Ha ◽  
Seong Baek Yoon ◽  
...  
Keyword(s):  
Deep Learning ◽  
Training Method ◽  
Noise Filter

A deep learning training method of water identification based on the Third National Land Survey data

2021 ◽  
Author(s):  
Zhida Chen ◽  
Chuan Lin ◽  
ChangLei Cao ◽  
Guang Gao ◽  
Liangzhong Ying
Keyword(s):  
Deep Learning ◽  
Survey Data ◽  
Training Method ◽  
The Third ◽  
Land Survey

Training Method of Deep Learning-Based Decoder for Punctured Polar Codes

2018 ◽  
Vol 43 (7) ◽  
pp. 1176-1181
Author(s):  
Eun Young Seo ◽  
Yeon Joon Choi ◽  
Jong-Hwan Kim ◽  
Sang-Hyo Kim
Keyword(s):  
Deep Learning ◽  
Polar Codes ◽  
Training Method

scholarly journals A Double-Branch Surface Detection System for Armatures in Vibration Motors with Miniature Volume Based on ResNet-101 and FPN

Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2360
Author(s):  
Tao Feng ◽  
Jiange Liu ◽  
Xia Fang ◽  
Jie Wang ◽  
Libin Zhou
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Complete System ◽  
Detection System ◽  
Discrimination Performance ◽  
Training Method ◽  
Production Lines ◽  
Training Set ◽  
Test Set

In this paper, a complete system based on computer vision and deep learning is proposed for surface inspection of the armatures in a vibration motor with miniature volume. A device for imaging and positioning was designed in order to obtain the images of the surface of the armatures. The images obtained by the device were divided into a training set and a test set. With continuous experimental exploration and improvement, the most efficient deep-network model was designed. The results show that the model leads to high accuracy on both the training set and the test set. In addition, we proposed a training method to make the network designed by us perform better. To guarantee the quality of the motor, a double-branch discrimination mechanism was also proposed. In order to verify the reliability of the system, experimental verification was conducted on the production line, and a satisfactory discrimination performance was reached. The results indicate that the proposed detection system for the armatures based on computer vision and deep learning is stable and reliable for armature production lines.

scholarly journals Face Recognition Based on Lightweight Convolutional Neural Networks

Information ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 191
Author(s):  
Wenting Liu ◽  
Li Zhou ◽  
Jie Chen
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Face Recognition ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Recognition Task ◽  
Training Method ◽  
The Face ◽  
And Storage ◽  
And Training

Face recognition algorithms based on deep learning methods have become increasingly popular. Most of these are based on highly precise but complex convolutional neural networks (CNNs), which require significant computing resources and storage, and are difficult to deploy on mobile devices or embedded terminals. In this paper, we propose several methods to improve the algorithms for face recognition based on a lightweight CNN, which is further optimized in terms of the network architecture and training pattern on the basis of MobileFaceNet. Regarding the network architecture, we introduce the Squeeze-and-Excitation (SE) block and propose three improved structures via a channel attention mechanism—the depthwise SE module, the depthwise separable SE module, and the linear SE module—which are able to learn the correlation of information between channels and assign them different weights. In addition, a novel training method for the face recognition task combined with an additive angular margin loss function is proposed that performs the compression and knowledge transfer of the deep network for face recognition. Finally, we obtained high-precision and lightweight face recognition models with fewer parameters and calculations that are more suitable for applications. Through extensive experiments and analysis, we demonstrate the effectiveness of the proposed methods.

scholarly journals STRUCTURE OPTIMIZATION OF DEEP BELIEF NETS IN THE APPLICATIONS OF IMAGE RECOGNITION.

2020 ◽  
Vol 9 (7) ◽  
pp. 179-189
Keyword(s):  
Deep Learning ◽  
Image Recognition ◽  
Structure Optimization ◽  
Reconstruction Error ◽  
Deep Belief Network ◽  
Training Method ◽  
Belief Network ◽  
Supervised Training ◽  
Training Resources ◽  
Hidden Layer

Deep belief network (DBN) has become one of the most important models in deep learning, however, the un-optimized structure leads to wasting too much training resources. To solve this problem and to investigate the connection of depth and accuracy of DBN, an optimization training method that consists of two steps is proposed. Firstly, by using mathematical and biological tools, the significance of supervised training is analyzed, and a theorem, that is on reconstruction error and network energy, is proved. Secondly, based on conclusions of step one, this paper proposes to optimize the structure of DBN (especially hidden layer numbers). Thirdly, this method is applied in two image recognition experiments, and results show increased computing efficiency and accuracies in both tasks.

Sign in / Sign up

Export Citation Format

Share Document