scholarly journals Empirical Frequentist Coverage of Deep Learning Uncertainty Quantification Procedures

Entropy ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. 1608
Author(s):  
Benjamin Kompa ◽  
Jasper Snoek ◽  
Andrew L. Beam
Keyword(s):  
Deep Learning ◽  
Uncertainty Quantification ◽  
Real World ◽  
Large Scale ◽  
Prediction Interval ◽  
Brier Score ◽  
Distribution Data ◽  
Calibration Error ◽  
Learning Models ◽  
Frequentist Coverage

Uncertainty quantification for complex deep learning models is increasingly important as these techniques see growing use in high-stakes, real-world settings. Currently, the quality of a model’s uncertainty is evaluated using point-prediction metrics, such as the negative log-likelihood (NLL), expected calibration error (ECE) or the Brier score on held-out data. Marginal coverage of prediction intervals or sets, a well-known concept in the statistical literature, is an intuitive alternative to these metrics but has yet to be systematically studied for many popular uncertainty quantification techniques for deep learning models. With marginal coverage and the complementary notion of the width of a prediction interval, downstream users of deployed machine learning models can better understand uncertainty quantification both on a global dataset level and on a per-sample basis. In this study, we provide the first large-scale evaluation of the empirical frequentist coverage properties of well-known uncertainty quantification techniques on a suite of regression and classification tasks. We find that, in general, some methods do achieve desirable coverage properties on in distribution samples, but that coverage is not maintained on out-of-distribution data. Our results demonstrate the failings of current uncertainty quantification techniques as dataset shift increases and reinforce coverage as an important metric in developing models for real-world applications.

scholarly journals EyeHealer: A large-scale anterior eye segment dataset with eye structure and lesion annotations

2021 ◽  
Author(s):  
Wenjia Cai ◽  
Jie Xu ◽  
Ke Wang ◽  
Xiaohong Liu ◽  
Wenqin Xu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Image Annotation ◽  
Clinical Care ◽  
Significant Proportion ◽  
Anterior Segment ◽  
Future Research ◽  
Learning Models ◽  
Anterior Eye Segment ◽  
Segmentation Models

Abstract Anterior segment eye diseases account for a significant proportion of presentations to eye clinics worldwide, including diseases associated with corneal pathologies, anterior chamber abnormalities (e.g. blood or inflammation) and lens diseases. The construction of an automatic tool for the segmentation of anterior segment eye lesions will greatly improve the efficiency of clinical care. With research on artificial intelligence progressing in recent years, deep learning models have shown their superiority in image classification and segmentation. The training and evaluation of deep learning models should be based on a large amount of data annotated with expertise, however, such data are relatively scarce in the domain of medicine. Herein, the authors developed a new medical image annotation system, called EyeHealer. It is a large-scale anterior eye segment dataset with both eye structures and lesions annotated at the pixel level. Comprehensive experiments were conducted to verify its performance in disease classification and eye lesion segmentation. The results showed that semantic segmentation models outperformed medical segmentation models. This paper describes the establishment of the system for automated classification and segmentation tasks. The dataset will be made publicly available to encourage future research in this area.

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 Validating the validation: reanalyzing a large-scale comparison of deep learning and machine learning models for bioactivity prediction

2020 ◽  
Vol 34 (7) ◽  
pp. 717-730 ◽  
Author(s):  
Matthew C. Robinson ◽  
Robert C. Glen ◽  
Alpha A. Lee
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Numerical Experiments ◽  
Large Scale ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Learning Models ◽  
Bioactivity Prediction ◽  
Operating Characteristic Curve ◽  
Machine Learning Models

Abstract Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should be benchmarked and validated. We reanalyze the data generated by a recently published large-scale comparison of machine learning models for bioactivity prediction and arrive at a somewhat different conclusion. We show that the performance of support vector machines is competitive with that of deep learning methods. Additionally, using a series of numerical experiments, we question the relevance of area under the receiver operating characteristic curve as a metric in virtual screening. We further suggest that area under the precision–recall curve should be used in conjunction with the receiver operating characteristic curve. Our numerical experiments also highlight challenges in estimating the uncertainty in model performance via scaffold-split nested cross validation.

scholarly journals Large-scale real-world radio signal recognition with deep learning

2021 ◽  
Author(s):  
Ya Tu ◽  
Yun Lin ◽  
Haoran Zha ◽  
Ju Zhang ◽  
Yu Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Real World ◽  
Large Scale ◽  
Radio Signal ◽  
Signal Recognition

scholarly journals A Hybrid Deep Learning System for Real-World Mobile User Authentication Using Motion Sensors

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 3876 ◽  
Author(s):  
Tiantian Zhu ◽  
Zhengqiu Weng ◽  
Guolang Chen ◽  
Lei Fu
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Mobile Devices ◽  
Real World ◽  
Large Scale ◽  
User Authentication ◽  
Mobile User ◽  
Learning System ◽  
Support Vector ◽  
Motion Sensors

With the popularity of smartphones and the development of hardware, mobile devices are widely used by people. To ensure availability and security, how to protect private data in mobile devices without disturbing users has become a key issue. Mobile user authentication methods based on motion sensors have been proposed by many works, but the existing methods have a series of problems such as poor de-noising ability, insufficient availability, and low coverage of feature extraction. Based on the shortcomings of existing methods, this paper proposes a hybrid deep learning system for complex real-world mobile authentication. The system includes: (1) a variational mode decomposition (VMD) based de-noising method to enhance the singular value of sensors, such as discontinuities and mutations, and increase the extraction range of the feature; (2) semi-supervised collaborative training (Tri-Training) methods to effectively deal with mislabeling problems in complex real-world situations; and (3) a combined convolutional neural network (CNN) and support vector machine (SVM) model for effective hybrid feature extraction and training. The training results under large-scale, real-world data show that the proposed system can achieve 95.01% authentication accuracy, and the effect is better than the existing frontier methods.

Biological Data Classification and Analysis Using Convolutional Neural Network

2020 ◽  
Vol 10 (10) ◽  
pp. 2459-2465
Author(s):  
Iftikhar Ahmad ◽  
Muhammad Javed Iqbal ◽  
Mohammad Basheri
Keyword(s):  
Deep Learning ◽  
Early Diagnosis ◽  
Language Processing ◽  
Large Scale ◽  
Genetic Diseases ◽  
Research Work ◽  
Biological Data ◽  
Learning Ability ◽  
Learning Models ◽  
Depth Analysis

The size of data gathered from various ongoing biological and clinically studies is increasing at an exponential rate. The bio-inspired data mainly comprises of genes of DNA, protein and variety of proteomics and genetic diseases. Additionally, DNA microarray data is also available for early diagnosis and prediction of various types of cancer diseases. Interestingly, this data may store very vital information about genes, their structure and important biological function. The huge volume and constant increase in the extracted bio data has opened several challenges. Many bioinformatics and machine learning models have been developed but those fail to address key challenges presents in the efficient and accurate analysis of variety of complex biologically inspired data such as genetic diseases etc. The reliable and robust process of classifying the extracted data into different classes based on the information hidden in the sample data is also a very interesting and open problem. This research work mainly focuses to overcome major challenges in the accurate protein classification keeping in view of the success of deep learning models in natural language processing since it assumes the proteins sequences as a language. The learning ability and overall classification performance of the proposed system can be validated with deep learning classification models. The proposed system can have the superior ability to accurately classify the mentioned datasets than previous approaches and shows better results. The in-depth analysis of multifaceted biological data may also help in the early diagnosis of diseases that causes due to mutation of genes and to overcome arising challenges in the development of large-scale healthcare systems.

Sign in / Sign up

Export Citation Format

Share Document