scholarly journals Generative-Discriminative Complementary Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 6526-6533
Author(s):  
Yanwu Xu ◽  
Mingming Gong ◽  
Junxiang Chen ◽  
Tongliang Liu ◽  
Kun Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Conditional Distribution ◽  
State Of The Art ◽  
Empirical Studies ◽  
Learning Method ◽  
Learning Problem ◽  
High Quality ◽  
Learning Methods ◽  
Weak Supervision

The majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminative complementary learning method that estimates the ordinary labels by modeling both the conditional (discriminative) and instance (generative) distributions. Our method, we call Complementary Conditional GAN (CCGAN), improves the accuracy of predicting ordinary labels and is able to generate high-quality instances in spite of weak supervision. In addition to the extensive empirical studies, we also theoretically show that our model can retrieve the true conditional distribution from the complementarily-labeled data.

scholarly journals Integrating Machine/Deep Learning Methods and Filtering Techniques for Reliable Mineral Phase Segmentation of 3D X-ray Computed Tomography Images

Energies ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4595
Author(s):  
Parisa Asadi ◽  
Lauren E. Beckingham
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Random Forest ◽  
Ct Images ◽  
Ct Imaging ◽  
Learning Method ◽  
Learning Methods ◽  
X Ray ◽  
Machine Learning Methods ◽  
Filtering Techniques

X-ray CT imaging provides a 3D view of a sample and is a powerful tool for investigating the internal features of porous rock. Reliable phase segmentation in these images is highly necessary but, like any other digital rock imaging technique, is time-consuming, labor-intensive, and subjective. Combining 3D X-ray CT imaging with machine learning methods that can simultaneously consider several extracted features in addition to color attenuation, is a promising and powerful method for reliable phase segmentation. Machine learning-based phase segmentation of X-ray CT images enables faster data collection and interpretation than traditional methods. This study investigates the performance of several filtering techniques with three machine learning methods and a deep learning method to assess the potential for reliable feature extraction and pixel-level phase segmentation of X-ray CT images. Features were first extracted from images using well-known filters and from the second convolutional layer of the pre-trained VGG16 architecture. Then, K-means clustering, Random Forest, and Feed Forward Artificial Neural Network methods, as well as the modified U-Net model, were applied to the extracted input features. The models’ performances were then compared and contrasted to determine the influence of the machine learning method and input features on reliable phase segmentation. The results showed considering more dimensionality has promising results and all classification algorithms result in high accuracy ranging from 0.87 to 0.94. Feature-based Random Forest demonstrated the best performance among the machine learning models, with an accuracy of 0.88 for Mancos and 0.94 for Marcellus. The U-Net model with the linear combination of focal and dice loss also performed well with an accuracy of 0.91 and 0.93 for Mancos and Marcellus, respectively. In general, considering more features provided promising and reliable segmentation results that are valuable for analyzing the composition of dense samples, such as shales, which are significant unconventional reservoirs in oil recovery.

scholarly journals Learning Feature Interactions with Lorentzian Factorization Machine

2020 ◽  
Vol 34 (04) ◽  
pp. 6470-6477
Author(s):  
Canran Xu ◽  
Ming Wu
Keyword(s):  
Deep Learning ◽  
Hyperbolic Space ◽  
Recommendation System ◽  
Triangle Inequality ◽  
State Of The Art ◽  
Learning Methods ◽  
New Model ◽  
User Behaviors ◽  
Feature Interactions ◽  
Factorization Machine

Learning representations for feature interactions to model user behaviors is critical for recommendation system and click-trough rate (CTR) predictions. Recent advances in this area are empowered by deep learning methods which could learn sophisticated feature interactions and achieve the state-of-the-art result in an end-to-end manner. These approaches require large number of training parameters integrated with the low-level representations, and thus are memory and computational inefficient. In this paper, we propose a new model named “LorentzFM” that can learn feature interactions embedded in a hyperbolic space in which the violation of triangle inequality for Lorentz distances is available. To this end, the learned representation is benefited by the peculiar geometric properties of hyperbolic triangles, and result in a significant reduction in the number of parameters (20% to 80%) because all the top deep learning layers are not required. With such a lightweight architecture, LorentzFM achieves comparable and even materially better results than the deep learning methods such as DeepFM, xDeepFM and Deep & Cross in both recommendation and CTR prediction tasks.

scholarly journals SCFont: Structure-Guided Chinese Font Generation via Deep Stacked Networks

2019 ◽  
Vol 33 ◽  
pp. 4015-4022 ◽  
Author(s):  
Yue Jiang ◽  
Zhouhui Lian ◽  
Yingmin Tang ◽  
Jianguo Xiao
Keyword(s):  
Deep Learning ◽  
Domain Knowledge ◽  
State Of The Art ◽  
Automatic Generation ◽  
Chinese Characters ◽  
Generation System ◽  
Model Learning ◽  
High Quality ◽  
Large Numbers ◽  
Quantitative Assessments

Automatic generation of Chinese fonts that consist of large numbers of glyphs with complicated structures is now still a challenging and ongoing problem in areas of AI and Computer Graphics (CG). Traditional CG-based methods typically rely heavily on manual interventions, while recentlypopularized deep learning-based end-to-end approaches often obtain synthesis results with incorrect structures and/or serious artifacts. To address those problems, this paper proposes a structure-guided Chinese font generation system, SCFont, by using deep stacked networks. The key idea is to integrate the domain knowledge of Chinese characters with deep generative networks to ensure that high-quality glyphs with correct structures can be synthesized. More specifically, we first apply a CNN model to learn how to transfer the writing trajectories with separated strokes in the reference font style into those in the target style. Then, we train another CNN model learning how to recover shape details on the contour for synthesized writing trajectories. Experimental results validate the superiority of the proposed SCFont compared to the state of the art in both visual and quantitative assessments.

scholarly journals Modulation Classification of Underwater Communication with Deep Learning Network

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Yan Wang ◽  
Hao Zhang ◽  
Zhanliang Sang ◽  
Lingwei Xu ◽  
Conghui Cao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Deep Learning ◽  
Language Processing ◽  
Communication Process ◽  
Underwater Acoustic Communication ◽  
Learning Method ◽  
Modulation Recognition ◽  
Learning Methods ◽  
Machine Learning Methods

Automatic modulation recognition has successfully used various machine learning methods and achieved certain results. As a subarea of machine learning, deep learning has made great progress in recent years and has made remarkable progress in the field of image and language processing. Deep learning requires a large amount of data support. As a communication field with a large amount of data, there is an inherent advantage of applying deep learning. However, the extensive application of deep learning in the field of communication has not yet been fully developed, especially in underwater acoustic communication. In this paper, we mainly discuss the modulation recognition process which is an important part of communication process by using the deep learning method. Different from the common machine learning methods that require feature extraction, the deep learning method does not require feature extraction and obtains more effects than common machine learning.

scholarly journals Single-Cell Phenotype Classification Using Deep Convolutional Neural Networks

2016 ◽  
Vol 21 (9) ◽  
pp. 998-1003 ◽  
Author(s):  
Oliver Dürr ◽  
Beate Sick
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Single Cell ◽  
Convolutional Neural Networks ◽  
State Of The Art ◽  
Misclassification Rate ◽  
Support Vector ◽  
Learning Methods ◽  
Phenotype Classification

Deep learning methods are currently outperforming traditional state-of-the-art computer vision algorithms in diverse applications and recently even surpassed human performance in object recognition. Here we demonstrate the potential of deep learning methods to high-content screening–based phenotype classification. We trained a deep learning classifier in the form of convolutional neural networks with approximately 40,000 publicly available single-cell images from samples treated with compounds from four classes known to lead to different phenotypes. The input data consisted of multichannel images. The construction of appropriate feature definitions was part of the training and carried out by the convolutional network, without the need for expert knowledge or handcrafted features. We compare our results against the recent state-of-the-art pipeline in which predefined features are extracted from each cell using specialized software and then fed into various machine learning algorithms (support vector machine, Fisher linear discriminant, random forest) for classification. The performance of all classification approaches is evaluated on an untouched test image set with known phenotype classes. Compared to the best reference machine learning algorithm, the misclassification rate is reduced from 8.9% to 6.6%.

scholarly journals Deep learning accurately predicts estrogen receptor status in breast cancer metabolomics data

2017 ◽  
Author(s):  
Fadhl M Alakwaa ◽  
Kumardeep Chaudhary ◽  
Lana X Garmire
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Estrogen Receptor ◽  
Deep Learning ◽  
Support Vector ◽  
Integrated Analysis ◽  
Learning Method ◽  
Learning Methods ◽  
Metabolomics Data ◽  
Machine Learning Methods

ABSTRACTMetabolomics holds the promise as a new technology to diagnose highly heterogeneous diseases. Conventionally, metabolomics data analysis for diagnosis is done using various statistical and machine learning based classification methods. However, it remains unknown if deep neural network, a class of increasingly popular machine learning methods, is suitable to classify metabolomics data. Here we use a cohort of 271 breast cancer tissues, 204 positive estrogen receptor (ER+) and 67 negative estrogen receptor (ER-), to test the accuracies of autoencoder, a deep learning (DL) framework, as well as six widely used machine learning models, namely Random Forest (RF), Support Vector Machines (SVM), Recursive Partitioning and Regression Trees (RPART), Linear Discriminant Analysis (LDA), Prediction Analysis for Microarrays (PAM), and Generalized Boosted Models (GBM). DL framework has the highest area under the curve (AUC) of 0.93 in classifying ER+/ER-patients, compared to the other six machine learning algorithms. Furthermore, the biological interpretation of the first hidden layer reveals eight commonly enriched significant metabolomics pathways (adjusted P-value<0.05) that cannot be discovered by other machine learning methods. Among them, protein digestion & absorption and ATP-binding cassette (ABC) transporters pathways are also confirmed in integrated analysis between metabolomics and gene expression data in these samples. In summary, deep learning method shows advantages for metabolomics based breast cancer ER status classification, with both the highest prediction accurcy (AUC=0.93) and better revelation of disease biology. We encourage the adoption of autoencoder based deep learning method in the metabolomics research community for classification.

scholarly journals Comparison of Soil Total Nitrogen Content Prediction Models Based on Vis-NIR Spectroscopy

Sensors ◽  
2020 ◽  
Vol 20 (24) ◽  
pp. 7078
Author(s):  
Yueting Wang ◽  
Minzan Li ◽  
Ronghua Ji ◽  
Minjuan Wang ◽  
Lihua Zheng
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Prediction Model ◽  
Total Nitrogen ◽  
Nir Spectroscopy ◽  
Learning Method ◽  
Learning Methods ◽  
Data Set ◽  
Machine Learning Methods ◽  
Conventional Machine

Visible-near-infrared spectrum (Vis-NIR) spectroscopy technology is one of the most important methods for non-destructive and rapid detection of soil total nitrogen (STN) content. In order to find a practical way to build STN content prediction model, three conventional machine learning methods and one deep learning approach are investigated and their predictive performances are compared and analyzed by using a public dataset called LUCAS Soil (19,019 samples). The three conventional machine learning methods include ordinary least square estimation (OLSE), random forest (RF), and extreme learning machine (ELM), while for the deep learning method, three different structures of convolutional neural network (CNN) incorporated Inception module are constructed and investigated. In order to clarify effectiveness of different pre-treatments on predicting STN content, the three conventional machine learning methods are combined with four pre-processing approaches (including baseline correction, smoothing, dimensional reduction, and feature selection) are investigated, compared, and analyzed. The results indicate that the baseline-corrected and smoothed ELM model reaches practical precision (coefficient of determination (R2) = 0.89, root mean square error of prediction (RMSEP) = 1.60 g/kg, and residual prediction deviation (RPD) = 2.34). While among three different structured CNN models, the one with more 1 × 1 convolutions preforms better (R2 = 0.93; RMSEP = 0.95 g/kg; and RPD = 3.85 in optimal case). In addition, in order to evaluate the influence of data set characteristics on the model, the LUCAS data set was divided into different data subsets according to dataset size, organic carbon (OC) content and countries, and the results show that the deep learning method is more effective and practical than conventional machine learning methods and, on the premise of enough data samples, it can be used to build a robust STN content prediction model with high accuracy for the same type of soil with similar agricultural treatment.

scholarly journals Comparison of Supervised and Unsupervised Deep Learning Methods for Medical Image Synthesis between Computed Tomography and Magnetic Resonance Images

2020 ◽  
Vol 2020 ◽  
pp. 1-9
Author(s):  
Yafen Li ◽  
Wen Li ◽  
Jing Xiong ◽  
Jun Xia ◽  
Yaoqin Xie
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Medical Image ◽  
Image Synthesis ◽  
Ct Images ◽  
Learning Method ◽  
Learning Methods ◽  
Unsupervised Deep Learning ◽  
Net Method ◽  
Synthetic Images

Cross-modality medical image synthesis between magnetic resonance (MR) images and computed tomography (CT) images has attracted increasing attention in many medical imaging area. Many deep learning methods have been used to generate pseudo-MR/CT images from counterpart modality images. In this study, we used U-Net and Cycle-Consistent Adversarial Networks (CycleGAN), which were typical networks of supervised and unsupervised deep learning methods, respectively, to transform MR/CT images to their counterpart modality. Experimental results show that synthetic images predicted by the proposed U-Net method got lower mean absolute error (MAE), higher structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR) in both directions of CT/MR synthesis, especially in synthetic CT image generation. Though synthetic images by the U-Net method has less contrast information than those by the CycleGAN method, the pixel value profile tendency of the synthetic images by the U-Net method is closer to the ground truth images. This work demonstrated that supervised deep learning method outperforms unsupervised deep learning method in accuracy for medical tasks of MR/CT synthesis.

scholarly journals A Mixed approach of Deep Learning method and Rule-Based method to improve Aspect Level Sentiment Analysis

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Paramita Ray ◽  
Amlan Chakrabarti
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
State Of The Art ◽  
The State ◽  
Learning Approach ◽  
Learning Method ◽  
Rule Based ◽  
Aspect Extraction ◽  
Art Methods ◽  
Rule Based Approach

Social networks have changed the communication patterns significantly. Information available from different social networking sites can be well utilized for the analysis of users opinion. Hence, the organizations would benefit through the development of a platform, which can analyze public sentiments in the social media about their products and services to provide a value addition in their business process. Over the last few years, deep learning is very popular in the areas of image classification, speech recognition, etc. However, research on the use of deep learning method in sentiment analysis is limited. It has been observed that in some cases the existing machine learning methods for sentiment analysis fail to extract some implicit aspects and might not be very useful. Therefore, we propose a deep learning approach for aspect extraction from text and analysis of users sentiment corresponding to the aspect. A seven layer deep convolutional neural network (CNN) is used to tag each aspect in the opinionated sentences. We have combined deep learning approach with a set of rule-based approach to improve the performance of aspect extraction method as well as sentiment scoring method. We have also tried to improve the existing rule-based approach of aspect extraction by aspect categorization with a predefined set of aspect categories using clustering method and compared our proposed method with some of the state-of-the-art methods. It has been observed that the overall accuracy of our proposed method is 0.87 while that of the other state-of-the-art methods like modified rule-based method and CNN are 0.75 and 0.80 respectively. The overall accuracy of our proposed method shows an increment of 7–12% from that of the state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document