scholarly journals Benign interpolation of noise in deep learning

2020 ◽  
Vol 32 (2) ◽  
Author(s):  
Marthinus Wilhelmus Theunissen ◽  
Marelie Davel ◽  
Etienne Barnard
Keyword(s):  
Deep Learning ◽  
Training Data ◽  
Multilayer Perceptrons ◽  
Neural Network Training ◽  
Learning Models ◽  
Network Training ◽  
Sample Data ◽  
Out Of Sample ◽  
Bias Variance ◽  
Deep Learning Model

The understanding of generalisation in machine learning is in a state of flux, in part due to the ability of deep learning models to interpolate noisy training data and still perform appropriately on out-of-sample data, thereby contradicting long-held intuitions about the bias-variance tradeoff in learning. We expand upon relevant existing work by discussing local attributes of neural network training within the context of a relatively simple framework. We describe how various types of noise can be compensated for within the proposed framework in order to allow the deep learning model to generalise in spite of interpolating spurious function descriptors. Empirically, we support our postulates with experiments involving overparameterised multilayer perceptrons and controlled training data noise. The main insights are that deep learning models are optimised for training data modularly, with different regions in the function space dedicated to fitting distinct types of sample information. Additionally, we show that models tend to fit uncorrupted samples first. Based on this finding, we propose a conjecture to explain an observed instance of the epoch-wise double-descent phenomenon. Our findings suggest that the notion of model capacity needs to be modified to consider the distributed way training data is fitted across sub-units.

scholarly journals A Physics-Infused Deep Learning Model for the Prediction of Refractive Indices and Its Use for the Large-Scale Screening of Organic Compound Space

2019 ◽  
Author(s):  
Mojtaba Haghighatlari ◽  
Gaurav Vishwakarma ◽  
Mohammad Atif Faiz Afzal ◽  
Johannes Hachmann
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Large Scale ◽  
Organic Molecules ◽  
Learning Model ◽  
Training Data ◽  
Refractive Indices ◽  
Learning Models ◽  
Deep Learning Model ◽  
Machine Learning Models

<div><div><div><p>We present a multitask, physics-infused deep learning model to accurately and efficiently predict refractive indices (RIs) of organic molecules, and we apply it to a library of 1.5 million compounds. We show that it outperforms earlier machine learning models by a significant margin, and that incorporating known physics into data-derived models provides valuable guardrails. Using a transfer learning approach, we augment the model to reproduce results consistent with higher-level computational chemistry training data, but with a considerably reduced number of corresponding calculations. Prediction errors of machine learning models are typically smallest for commonly observed target property values, consistent with the distribution of the training data. However, since our goal is to identify candidates with unusually large RI values, we propose a strategy to boost the performance of our model in the remoter areas of the RI distribution: We bias the model with respect to the under-represented classes of molecules that have values in the high-RI regime. By adopting a metric popular in web search engines, we evaluate our effectiveness in ranking top candidates. We confirm that the models developed in this study can reliably predict the RIs of the top 1,000 compounds, and are thus able to capture their ranking. We believe that this is the first study to develop a data-derived model that ensures the reliability of RI predictions by model augmentation in the extrapolation region on such a large scale. These results underscore the tremendous potential of machine learning in facilitating molecular (hyper)screening approaches on a massive scale and in accelerating the discovery of new compounds and materials, such as organic molecules with high-RI for applications in opto-electronics.</p></div></div></div>

scholarly journals Proactive Congestion Avoidance for Distributed Deep Learning

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 174
Author(s):  
Minkoo Kang ◽  
Gyeongsik Yang ◽  
Yeonho Yoo ◽  
Chuck Yoo
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Queue Length ◽  
Deep Neural Network ◽  
Congestion Avoidance ◽  
Model Parameters ◽  
Neural Network Training ◽  
Network Congestion ◽  
Network Training ◽  
Deep Learning Model

This paper presents “Proactive Congestion Notification” (PCN), a congestion-avoidance technique for distributed deep learning (DDL). DDL is widely used to scale out and accelerate deep neural network training. In DDL, each worker trains a copy of the deep learning model with different training inputs and synchronizes the model gradients at the end of each iteration. However, it is well known that the network communication for synchronizing model parameters is the main bottleneck in DDL. Our key observation is that the DDL architecture makes each worker generate burst traffic every iteration, which causes network congestion and in turn degrades the throughput of DDL traffic. Based on this observation, the key idea behind PCN is to prevent potential congestion by proactively regulating the switch queue length before DDL burst traffic arrives at the switch, which prepares the switches for handling incoming DDL bursts. In our evaluation, PCN improves the throughput of DDL traffic by 72% on average.

scholarly journals A Physics-Infused Deep Learning Model for the Prediction of Refractive Indices and Its Use for the Large-Scale Screening of Organic Compound Space

2019 ◽  
Author(s):  
Mojtaba Haghighatlari ◽  
Gaurav Vishwakarma ◽  
Mohammad Atif Faiz Afzal ◽  
Johannes Hachmann
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Large Scale ◽  
Organic Molecules ◽  
Learning Model ◽  
Training Data ◽  
Refractive Indices ◽  
Learning Models ◽  
Deep Learning Model ◽  
Machine Learning Models

<div><div><div><p>We present a multitask, physics-infused deep learning model to accurately and efficiently predict refractive indices (RIs) of organic molecules, and we apply it to a library of 1.5 million compounds. We show that it outperforms earlier machine learning models by a significant margin, and that incorporating known physics into data-derived models provides valuable guardrails. Using a transfer learning approach, we augment the model to reproduce results consistent with higher-level computational chemistry training data, but with a considerably reduced number of corresponding calculations. Prediction errors of machine learning models are typically smallest for commonly observed target property values, consistent with the distribution of the training data. However, since our goal is to identify candidates with unusually large RI values, we propose a strategy to boost the performance of our model in the remoter areas of the RI distribution: We bias the model with respect to the under-represented classes of molecules that have values in the high-RI regime. By adopting a metric popular in web search engines, we evaluate our effectiveness in ranking top candidates. We confirm that the models developed in this study can reliably predict the RIs of the top 1,000 compounds, and are thus able to capture their ranking. We believe that this is the first study to develop a data-derived model that ensures the reliability of RI predictions by model augmentation in the extrapolation region on such a large scale. These results underscore the tremendous potential of machine learning in facilitating molecular (hyper)screening approaches on a massive scale and in accelerating the discovery of new compounds and materials, such as organic molecules with high-RI for applications in opto-electronics.</p></div></div></div>

scholarly journals Deep Learning Model Comparison for Vision-Based Classification of Full/Empty-Load Trucks in Earthmoving Operations

2019 ◽  
Vol 9 (22) ◽  
pp. 4871 ◽  
Author(s):  
Quan Liu ◽  
Chen Feng ◽  
Zida Song ◽  
Joseph Louis ◽  
Jian Zhou
Keyword(s):  
Deep Learning ◽  
Model Comparison ◽  
Surveillance Systems ◽  
Comparison Study ◽  
Learning Models ◽  
The Core ◽  
Dump Trucks ◽  
Deep Learning Model ◽  
Contact Field

Earthmoving is an integral civil engineering operation of significance, and tracking its productivity requires the statistics of loads moved by dump trucks. Since current truck loads’ statistics methods are laborious, costly, and limited in application, this paper presents the framework of a novel, automated, non-contact field earthmoving quantity statistics (FEQS) for projects with large earthmoving demands that use uniform and uncovered trucks. The proposed FEQS framework utilizes field surveillance systems and adopts vision-based deep learning for full/empty-load truck classification as the core work. Since convolutional neural network (CNN) and its transfer learning (TL) forms are popular vision-based deep learning models and numerous in type, a comparison study is conducted to test the framework’s core work feasibility and evaluate the performance of different deep learning models in implementation. The comparison study involved 12 CNN or CNN-TL models in full/empty-load truck classification, and the results revealed that while several provided satisfactory performance, the VGG16-FineTune provided the optimal performance. This proved the core work feasibility of the proposed FEQS framework. Further discussion provides model choice suggestions that CNN-TL models are more feasible than CNN prototypes, and models that adopt different TL methods have advantages in either working accuracy or speed for different tasks.

scholarly journals Domain randomization-enhanced deep learning models for bird detection

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xin Mao ◽  
Jun Kang Chow ◽  
Pin Siang Tan ◽  
Kuan-fu Liu ◽  
Jimmy Wu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Continuous Monitoring ◽  
Bird Species ◽  
Training Data ◽  
Learning Models ◽  
Fine Grained ◽  
Bird Detection ◽  
Relationship Of ◽  
The Relationship

AbstractAutomatic bird detection in ornithological analyses is limited by the accuracy of existing models, due to the lack of training data and the difficulties in extracting the fine-grained features required to distinguish bird species. Here we apply the domain randomization strategy to enhance the accuracy of the deep learning models in bird detection. Trained with virtual birds of sufficient variations in different environments, the model tends to focus on the fine-grained features of birds and achieves higher accuracies. Based on the 100 terabytes of 2-month continuous monitoring data of egrets, our results cover the findings using conventional manual observations, e.g., vertical stratification of egrets according to body size, and also open up opportunities of long-term bird surveys requiring intensive monitoring that is impractical using conventional methods, e.g., the weather influences on egrets, and the relationship of the migration schedules between the great egrets and little egrets.

scholarly journals U-Infuse: Democratization of Customizable Deep Learning for Object Detection

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2611
Author(s):  
Andrew Shepley ◽  
Greg Falzon ◽  
Christopher Lawson ◽  
Paul Meek ◽  
Paul Kwan
Keyword(s):  
Deep Learning ◽  
Intellectual Property ◽  
Object Detection ◽  
Image Data ◽  
Learning Technologies ◽  
Training Data ◽  
Learning Models ◽  
Ecological Data ◽  
Single Class ◽  
Large Numbers

Image data is one of the primary sources of ecological data used in biodiversity conservation and management worldwide. However, classifying and interpreting large numbers of images is time and resource expensive, particularly in the context of camera trapping. Deep learning models have been used to achieve this task but are often not suited to specific applications due to their inability to generalise to new environments and inconsistent performance. Models need to be developed for specific species cohorts and environments, but the technical skills required to achieve this are a key barrier to the accessibility of this technology to ecologists. Thus, there is a strong need to democratize access to deep learning technologies by providing an easy-to-use software application allowing non-technical users to train custom object detectors. U-Infuse addresses this issue by providing ecologists with the ability to train customised models using publicly available images and/or their own images without specific technical expertise. Auto-annotation and annotation editing functionalities minimize the constraints of manually annotating and pre-processing large numbers of images. U-Infuse is a free and open-source software solution that supports both multiclass and single class training and object detection, allowing ecologists to access deep learning technologies usually only available to computer scientists, on their own device, customised for their application, without sharing intellectual property or sensitive data. It provides ecological practitioners with the ability to (i) easily achieve object detection within a user-friendly GUI, generating a species distribution report, and other useful statistics, (ii) custom train deep learning models using publicly available and custom training data, (iii) achieve supervised auto-annotation of images for further training, with the benefit of editing annotations to ensure quality datasets. Broad adoption of U-Infuse by ecological practitioners will improve ecological image analysis and processing by allowing significantly more image data to be processed with minimal expenditure of time and resources, particularly for camera trap images. Ease of training and use of transfer learning means domain-specific models can be trained rapidly, and frequently updated without the need for computer science expertise, or data sharing, protecting intellectual property and privacy.

scholarly journals A Deep Learning Model Using Satellite Ocean Color and Hydrodynamic Model to Estimate Chlorophyll-a Concentration

2021 ◽  
Vol 13 (10) ◽  
pp. 2003
Author(s):  
Daeyong Jin ◽  
Eojin Lee ◽  
Kyonghwan Kwon ◽  
Taeyun Kim
Keyword(s):  
Deep Learning ◽  
Chlorophyll A ◽  
Hydrodynamic Model ◽  
Ocean Color ◽  
Learning Model ◽  
Training Data ◽  
Coefficient Of Determination ◽  
Temporal And Spatial Distribution ◽  
Deep Learning Model ◽  
Satellite Ocean Color

In this study, we used convolutional neural networks (CNNs)—which are well-known deep learning models suitable for image data processing—to estimate the temporal and spatial distribution of chlorophyll-a in a bay. The training data required the construction of a deep learning model acquired from the satellite ocean color and hydrodynamic model. Chlorophyll-a, total suspended sediment (TSS), visibility, and colored dissolved organic matter (CDOM) were extracted from the satellite ocean color data, and water level, currents, temperature, and salinity were generated from the hydrodynamic model. We developed CNN Model I—which estimates the concentration of chlorophyll-a using a 48 × 27 sized overall image—and CNN Model II—which uses a 7 × 7 segmented image. Because the CNN Model II conducts estimation using only data around the points of interest, the quantity of training data is more than 300 times larger than that of CNN Model I. Consequently, it was possible to extract and analyze the inherent patterns in the training data, improving the predictive ability of the deep learning model. The average root mean square error (RMSE), calculated by applying CNN Model II, was 0.191, and when the prediction was good, the coefficient of determination (R2) exceeded 0.91. Finally, we performed a sensitivity analysis, which revealed that CDOM is the most influential variable in estimating the spatiotemporal distribution of chlorophyll-a.

scholarly journals Performance Comparison of the Deep Learning and the Human Endoscopist for Bleeding Peptic Ulcer Disease

2021 ◽  
Author(s):  
Hsu-Heng Yen ◽  
Ping-Yu Wu ◽  
Pei-Yuan Su ◽  
Chia-Wei Yang ◽  
Yang-Yuan Chen ◽  
...  
Keyword(s):  
Peptic Ulcer ◽  
Deep Learning ◽  
Sensitivity And Specificity ◽  
Endoscopic Therapy ◽  
Learning Model ◽  
Ulcer Bleeding ◽  
Learning Models ◽  
Peptic Ulcer Bleeding ◽  
Ulcer Disease ◽  
Deep Learning Model

Abstract Purpose Management of peptic ulcer bleeding is clinically challenging. Accurate characterization of the bleeding during endoscopy is key for endoscopic therapy. This study aimed to assess whether a deep learning model can aid in the classification of bleeding peptic ulcer disease. Methods Endoscopic still images of patients (n = 1694) with peptic ulcer bleeding for the last 5 years were retrieved and reviewed. Overall, 2289 images were collected for deep learning model training, and 449 images were validated for the performance test. Two expert endoscopists classified the images into different classes based on their appearance. Four deep learning models, including Mobile Net V2, VGG16, Inception V4, and ResNet50, were proposed and pre-trained by ImageNet with the established convolutional neural network algorithm. A comparison of the endoscopists and trained deep learning model was performed to evaluate the model’s performance on a dataset of 449 testing images. Results The results first presented the performance comparisons of four deep learning models. The Mobile Net V2 presented the optimal performance of the proposal models. The Mobile Net V2 was chosen for further comparing the performance with the diagnostic results obtained by one senior and one novice endoscopists. The sensitivity and specificity were acceptable for the prediction of “normal” lesions in both 3-class and 4-class classifications. For the 3-class category, the sensitivity and specificity were 94.83% and 92.36%, respectively. For the 4-class category, the sensitivity and specificity were 95.40% and 92.70%, respectively. The interobserver agreement of the testing dataset of the model was moderate to substantial with the senior endoscopist. The accuracy of the determination of endoscopic therapy required and high-risk endoscopic therapy of the deep learning model was higher than that of the novice endoscopist. Conclusions In this study, the deep learning model performed better than inexperienced endoscopists. Further improvement of the model may aid in clinical decision-making during clinical practice, especially for trainee endoscopist.

AOHDL: Archimedes Optimization Based Hybrid Deep Learning Model for Soybean Plant Disease Classification

2021 ◽  
Author(s):  
J. Annrose ◽  
N. Herald Anantha Rufus ◽  
C. R. Edwin Selva Rex ◽  
D. Godwin Immanuel
Keyword(s):  
Deep Learning ◽  
Optimization Algorithm ◽  
Short Term Memory ◽  
Learning Model ◽  
Disease Classification ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Soybean Plant ◽  
Lower Accuracy ◽  
Deep Learning Model

Abstract Bean which is botanically called Phaseolus vulgaris L belongs to the Fabaceae family.During bean disease identification, unnecessary economical losses occur due to the delay of the treatment period, incorrect treatment, and lack of knowledge. The existing deep learning and machine learning techniques met few issues such as high computational complexity, higher cost associated with the training data, more execution time, noise, feature dimensionality, lower accuracy, low speed, etc. To tackle these problems, we have proposed a hybrid deep learning model with an Archimedes optimization algorithm (HDL-AOA) for bean disease classification. In this work, there are five bean classes of which one is a healthy class whereas the remaining four classes indicate different diseases such as Bean halo blight, Pythium diseases, Rhizoctonia root rot, and Anthracnose abnormalities acquired from the Soybean (Large) Data Set.The hybrid deep learning technique is the combination of wavelet packet decomposition (WPD) and long short term memory (LSTM). Initially, the WPD decomposes the input images into four sub-series. For these sub-series, four LSTM networks were developed. During bean disease classification, an Archimedes optimization algorithm (AOA) enhances the classification accuracy for multiple single LSTM networks. MATLAB software implements the HDL-AOA model for bean disease classification. The proposed model accomplishes lower MAPE than other exiting methods. Finally, the proposed HDL-AOA model outperforms excellent classification results using different evaluation measures such as accuracy, specificity, sensitivity, precision, recall, and F-score.

Transfer Learning of The ResNet-18 and DenseNet-121 Model Used to Diagnose Intracranial Hemorrhage in CT Scanning

2021 ◽  
Vol 27 ◽  
Author(s):  
Qi Zhou ◽  
Wenjie Zhu ◽  
Fuchen Li ◽  
Mingqing Yuan ◽  
Linfeng Zheng ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Intracranial Hemorrhage ◽  
Intraventricular Hemorrhage ◽  
Learning Model ◽  
Normal Group ◽  
Subdural Hemorrhage ◽  
Model Assessment ◽  
Learning Models ◽  
Deep Learning Model

Objective: To verify the ability of the deep learning model in identifying five subtypes and normal images in noncontrast enhancement CT of intracranial hemorrhage. Method: A total of 351 patients (39 patients in the normal group, 312 patients in the intracranial hemorrhage group) performed with intracranial hemorrhage noncontrast enhanced CT were selected, with 2768 images in total (514 images for the normal group, 398 images for the epidural hemorrhage group, 501 images for the subdural hemorrhage group, 497 images for the intraventricular hemorrhage group, 415 images for the cerebral parenchymal hemorrhage group, and 443 images for the subarachnoid hemorrhage group). Based on the diagnostic reports of two radiologists with more than 10 years of experience, the ResNet-18 and DenseNet-121 deep learning models were selected. Transfer learning was used. 80% of the data was used for training models, 10% was used for validating model performance against overfitting, and the last 10% was used for the final evaluation of the model. Assessment indicators included accuracy, sensitivity, specificity, and AUC values. Results: The overall accuracy of ResNet-18 and DenseNet-121 models were 89.64% and 82.5%, respectively. The sensitivity and specificity of identifying five subtypes and normal images were above 0.80. The sensitivity of DenseNet-121 model to recognize intraventricular hemorrhage and cerebral parenchymal hemorrhage was lower than 0.80, 0.73, and 0.76 respectively. The AUC values of the two deep learning models were above 0.9. Conclusion: The deep learning model can accurately identify the five subtypes of intracranial hemorrhage and normal images, and it can be used as a new tool for clinical diagnosis in the future.

Sign in / Sign up

Export Citation Format

Share Document