Relevant bibliographies by topics / Machine Learning Model Robustness

Academic literature on the topic 'Machine Learning Model Robustness'

Author: Grafiati
Published: 9 March 2023
Last updated: 11 March 2023

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Contents

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Machine Learning Model Robustness.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "Machine Learning Model Robustness"

1

Arslan, Ayse. "Rethinking Robustness in Machine Learning: Use of Generative Adversarial Networks for Enhanced Robustness." Scholars Journal of Engineering and Technology 10, no. 3 (March 28, 2022): 9–15. http://dx.doi.org/10.36347/sjet.2022.v10i03.001.

Full text
Abstract:
Machine learning (ML) is increasingly being used in real-world applications, so understanding the uncertainty and robustness of a model is necessary to ensure performance in practice. This paper explores approximations for robustness which can meaningfully explain the behavior of any black box model. Starting with a discussion on components of a robust model this paper offers some techniques based on the Generative Adversarial Network (GAN) approach to improve the robustness of a model. The study concludes that a clear understanding of robust models for ML allows improving information for practitioners, and helps to develop tools that assess the robustness of ML. Also, ML tools and libraries could benefit from a clear understanding on how information should be presented and how these tools are used.
APA, Harvard, Vancouver, ISO, and other styles
2

Einziger, Gil, Maayan Goldstein, Yaniv Sa’ar, and Itai Segall. "Verifying Robustness of Gradient Boosted Models." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 2446–53. http://dx.doi.org/10.1609/aaai.v33i01.33012446.

Full text
Abstract:
Gradient boosted models are a fundamental machine learning technique. Robustness to small perturbations of the input is an important quality measure for machine learning models, but the literature lacks a method to prove the robustness of gradient boosted models.This work introduces VERIGB, a tool for quantifying the robustness of gradient boosted models. VERIGB encodes the model and the robustness property as an SMT formula, which enables state of the art verification tools to prove the model’s robustness. We extensively evaluate VERIGB on publicly available datasets and demonstrate a capability for verifying large models. Finally, we show that some model configurations tend to be inherently more robust than others.
APA, Harvard, Vancouver, ISO, and other styles
3

Thapa, Chandra, Pathum Chamikara Mahawaga Arachchige, Seyit Camtepe, and Lichao Sun. "SplitFed: When Federated Learning Meets Split Learning." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 8 (June 28, 2022): 8485–93. http://dx.doi.org/10.1609/aaai.v36i8.20825.

Full text
Abstract:
Federated learning (FL) and split learning (SL) are two popular distributed machine learning approaches. Both follow a model-to-data scenario; clients train and test machine learning models without sharing raw data. SL provides better model privacy than FL due to the machine learning model architecture split between clients and the server. Moreover, the split model makes SL a better option for resource-constrained environments. However, SL performs slower than FL due to the relay-based training across multiple clients. In this regard, this paper presents a novel approach, named splitfed learning (SFL), that amalgamates the two approaches eliminating their inherent drawbacks, along with a refined architectural configuration incorporating differential privacy and PixelDP to enhance data privacy and model robustness. Our analysis and empirical results demonstrate that (pure) SFL provides similar test accuracy and communication efficiency as SL while significantly decreasing its computation time per global epoch than in SL for multiple clients. Furthermore, as in SL, its communication efficiency over FL improves with the number of clients. Besides, the performance of SFL with privacy and robustness measures is further evaluated under extended experimental settings.
APA, Harvard, Vancouver, ISO, and other styles
4

Balakrishnan, Charumathi, and Mangaiyarkarasi Thiagarajan. "CREDIT RISK MODELLING FOR INDIAN DEBT SECURITIES USING MACHINE LEARNING." Buletin Ekonomi Moneter dan Perbankan 24 (March 8, 2021): 107–28. http://dx.doi.org/10.21098/bemp.v24i0.1401.

Full text
Abstract:
We develop a new credit risk model for Indian debt securities rated by major credit rating agencies in India using the ordinal logistic regression (OLR). The robustness of the model is tested by comparing it with classical models available for ratings prediction. We improved the model’s accuracy by using machine learning techniques, such as the artificial neural networks (ANN), support vector machines (SVM) and random forest (RF). We found that the accuracy of our model has improved from 68% using OLR to 82% when using ANN and above 90% when using SVM and RF.
APA, Harvard, Vancouver, ISO, and other styles
5

Nguyen, Ngoc-Kim-Khanh, Quang Nguyen, Hai-Ha Pham, Thi-Trang Le, Tuan-Minh Nguyen, Davide Cassi, Francesco Scotognella, Roberto Alfierif, and Michele Bellingeri. "Predicting the Robustness of Large Real-World Social Networks Using a Machine Learning Model." Complexity 2022 (November 9, 2022): 1–16. http://dx.doi.org/10.1155/2022/3616163.

Full text
Abstract:
Computing the robustness of a network, i.e., the capacity of a network holding its main functionality when a proportion of its nodes/edges are damaged, is useful in many real applications. The Monte Carlo numerical simulation is the commonly used method to compute network robustness. However, it has a very high computational cost, especially for large networks. Here, we propose a methodology such that the robustness of large real-world social networks can be predicted using machine learning models, which are pretrained using existing datasets. We demonstrate this approach by simulating two effective node attack strategies, i.e., the recalculated degree (RD) and initial betweenness (IB) node attack strategies, and predicting network robustness by using two machine learning models, multiple linear regression (MLR) and the random forest (RF) algorithm. We use the classic network robustness metric R as a model response and 8 network structural indicators (NSI) as predictor variables and trained over a large dataset of 48 real-world social networks, whose maximum number of nodes is 265,000. We found that the RF model can predict network robustness with a mean squared error (RMSE) of 0.03 and is 30% better than the MLR model. Among the results, we found that the RD strategy has more efficacy than IB for attacking real-world social networks. Furthermore, MLR indicates that the most important factors to predict network robustness are the scale-free exponent α and the average node degree <k>. On the contrary, the RF indicates that degree assortativity a, the global closeness, and the average node degree <k> are the most important factors. This study shows that machine learning models can be a promising way to infer social network robustness.
APA, Harvard, Vancouver, ISO, and other styles
6

Wu, Zhijing, and Hua Xu. "A Multi-Task Learning Machine Reading Comprehension Model for Noisy Document (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 10 (April 3, 2020): 13963–64. http://dx.doi.org/10.1609/aaai.v34i10.7254.

Full text
Abstract:
Current neural models for Machine Reading Comprehension (MRC) have achieved successful performance in recent years. However, the model is too fragile and lack robustness to tackle the imperceptible adversarial perturbations to the input. In this work, we propose a multi-task learning MRC model with a hierarchical knowledge enrichment to further improve the robustness for noisy document. Our model follows a typical encode-align-decode framework. Additionally, we apply a hierarchical method of adding background knowledge into the model from coarse-to-fine to enhance the language representations. Besides, we optimize our model by jointly training the answer span and unanswerability prediction, aiming to improve the robustness to noise. Experiment results on benchmark datasets confirm the superiority of our method, and our method can achieve competitive performance compared with other strong baselines.
APA, Harvard, Vancouver, ISO, and other styles
7

Chuah, Joshua, Uwe Kruger, Ge Wang, Pingkun Yan, and Juergen Hahn. "Framework for Testing Robustness of Machine Learning-Based Classifiers." Journal of Personalized Medicine 12, no. 8 (August 14, 2022): 1314. http://dx.doi.org/10.3390/jpm12081314.

Full text
Abstract:
There has been a rapid increase in the number of artificial intelligence (AI)/machine learning (ML)-based biomarker diagnostic classifiers in recent years. However, relatively little work has focused on assessing the robustness of these biomarkers, i.e., investigating the uncertainty of the AI/ML models that these biomarkers are based upon. This paper addresses this issue by proposing a framework to evaluate the already-developed classifiers with regard to their robustness by focusing on the variability of the classifiers’ performance and changes in the classifiers’ parameter values using factor analysis and Monte Carlo simulations. Specifically, this work evaluates (1) the importance of a classifier’s input features and (2) the variability of a classifier’s output and model parameter values in response to data perturbations. Additionally, it was found that one can estimate a priori how much replacement noise a classifier can tolerate while still meeting accuracy goals. To illustrate the evaluation framework, six different AI/ML-based biomarkers are developed using commonly used techniques (linear discriminant analysis, support vector machines, random forest, partial-least squares discriminant analysis, logistic regression, and multilayer perceptron) for a metabolomics dataset involving 24 measured metabolites taken from 159 study participants. The framework was able to correctly predict which of the classifiers should be less robust than others without recomputing the classifiers itself, and this prediction was then validated in a detailed analysis.
APA, Harvard, Vancouver, ISO, and other styles
8

Sepulveda, Natalia Espinoza, and Jyoti Sinha. "Parameter Optimisation in the Vibration-Based Machine Learning Model for Accurate and Reliable Faults Diagnosis in Rotating Machines." Machines 8, no. 4 (October 23, 2020): 66. http://dx.doi.org/10.3390/machines8040066.

Full text
Abstract:
Artificial intelligence (AI)-based machine learning (ML) models seem to be the future for most of the applications. Recent research effort has also been made on the application of these AI and ML methods in the vibration-based faults diagnosis (VFD) in rotating machines. Several research studies have been published over the last decade on this topic. However, most of the studies are data driven, and the vibration-based ML (VML) model is generally developed on a typical machine. The developed VML model may not predict faults accurately if applied on other identical machines or a machine with different operation conditions or both. Therefore, the current research is on the development of a VML model by optimising the vibration parameters based on the dynamics of the machine. The developed model is then blindly tested at different machine operation conditions to show the robustness and reliability of the proposed VML model.
APA, Harvard, Vancouver, ISO, and other styles
9

Zhang, Lingwen, Ning Xiao, Wenkao Yang, and Jun Li. "Advanced Heterogeneous Feature Fusion Machine Learning Models and Algorithms for Improving Indoor Localization." Sensors 19, no. 1 (January 2, 2019): 125. http://dx.doi.org/10.3390/s19010125.

Full text
Abstract:
In the era of the Internet of Things and Artificial Intelligence, the Wi-Fi fingerprinting-based indoor positioning system (IPS) has been recognized as the most promising IPS for various applications. Fingerprinting-based algorithms critically rely on a fingerprint database built from machine learning methods. However, currently methods are based on single-feature Received Signal Strength (RSS), which is extremely unstable in performance in terms of precision and robustness. The reason for this is that single feature machines cannot capture the complete channel characteristics and are susceptible to interference. The objective of this paper is to exploit the Time of Arrival (TOA) feature and propose a heterogeneous features fusion model to enhance the precision and robustness of indoor positioning. Several challenges are addressed: (1) machine learning models based on heterogeneous features, (2) the optimization of algorithms for high precision and robustness, and (3) computational complexity. This paper provides several heterogeneous features fusion-based localization models. Their effectiveness and efficiency are thoroughly compared with state-of-the-art methods.
APA, Harvard, Vancouver, ISO, and other styles
10

Drews, Samuel, Aws Albarghouthi, and Loris D'Antoni. "Proving Data-Poisoning Robustness in Decision Trees." Communications of the ACM 66, no. 2 (January 20, 2023): 105–13. http://dx.doi.org/10.1145/3576894.

Full text
Abstract:
Machine learning models are brittle, and small changes in the training data can result in different predictions. We study the problem of proving that a prediction is robust to data poisoning , where an attacker can inject a number of malicious elements into the training set to influence the learned model. We target decision tree models, a popular and simple class of machine learning models that underlies many complex learning techniques. We present a sound verification technique based on abstract interpretation and implement it in a tool called Antidote. Antidote abstractly trains decision trees for an intractably large space of possible poisoned datasets. Due to the soundness of our abstraction, Antidote can produce proofs that, for a given input, the corresponding prediction would not have changed had the training set been tampered with or not. We demonstrate the effectiveness of Antidote on a number of popular datasets.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "Machine Learning Model Robustness"

1

Adams, William A. "Analysis of Robustness in Lane Detection using Machine Learning Models." Ohio University / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1449167611.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Lundström, Linnea. "Formally Verifying the Robustness of Machine Learning Models : A Comparative Study." Thesis, Linköpings universitet, Programvara och system, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-167504.

Full text
Abstract:
Machine learning models have become increasingly popular in recent years, and not without reason. They enable software to become more powerful, and with less human involvement. As a consequence however, the actions of the software are hard for a human to understand and anticipate. This prohibits the use of machine learning in systems where safety has to be assured, typically using formal proofs of relevant properties. This thesis is focused on robustness - one of many properties that can impact the safety of a system. There are several tools available that enable formal robustness verification of machine learning models, and a goal of this thesis is to evaluate their performance. A variety of machine learning models are also assessed according to how robust they can be proved to be. A digit recognition problem was used in order to evaluate how sensitive different model types are to perturbations of pixels in an image, and also to assess the performance of applicable verification tools. On this particular problem, we discovered that a Support Vector Machine demonstrates the highest degree of robustness, which could be verified with short enough time using the tool SAVer. In addition, machine learning models were trained on a data set consisting of Android applications that are labelled either as malware or benign. In this verification problem, we check whether adding permission requests to an application that is malware can make it become labelled as benign. For this problem, a Gradient Boosting Machine proved to be the most robust with a very short verification time using the tool VoTE. Although not the most robust, Neural Networks were proved to be relatively robust on both problems using the tool ERAN, whereas Random Forests performed the worst, in terms of robustness.
APA, Harvard, Vancouver, ISO, and other styles
3

MAURI, LARA. "DATA PARTITIONING AND COMPENSATION TECHNIQUES FOR SECURE TRAINING OF MACHINE LEARNING MODELS." Doctoral thesis, Università degli Studi di Milano, 2022. http://hdl.handle.net/2434/932387.

Full text
Abstract:
Advances in Machine Learning (ML), coupled with increased availability of huge amounts of data collected from diverse sources and improvements in computing power, have led to a widespread adoption of ML-based solutions in critical application scenarios. However, ML models intrinsically introduce new security vulnerabilities within the systems into which they are integrated, thereby expanding their attack surface. The security of ML-based systems hinges on the robustness of the ML model employed. By interfering with any of the phases of the learning process, an adversary can manipulate data and prevent the model from learning the correct correlations or mislead it into taking potentially harmful actions. Adversarial ML is a recent research field that addresses two specific research topics. One of them concerns the identification of security issues related to the use of ML models, and the other concerns the design of defense mechanisms to prevent or mitigate the detrimental effects of attacks. In this dissertation, we investigate how to improve the resilience of ML models against training-time attacks under black-box knowledge assumption on both the attacker and the defender. The main contribution of this work is a novel defense mechanism which combines ensemble models (an approach traditionally used only for increasing the generalization capabilities of the model) and security risk analysis. Specifically, the results from the risk analysis in the input data space are used to guide the partitioning of the training data via an unsupervised technique. Then, we employ an ensemble of models, each trained on a different partition, and combine their output based on a majority voting mechanism to obtain the final prediction. Experiments are carried out on a publicly available dataset to assess the effectiveness of the proposed method. This novel defence technique is complemented by two other contributions, which respectively support using a Distributed Ledger to make training data tampering less convenient for attackers, and using a quantitative index to compute ML models’ performance degradation before and after the deployment of the defense. Taken together, this set of techniques provides a framework to improve the robustness of the ML lifecycle.
APA, Harvard, Vancouver, ISO, and other styles
4

Rado, Omesaad A. M. "Contributions to evaluation of machine learning models. Applicability domain of classification models." Thesis, University of Bradford, 2019. http://hdl.handle.net/10454/18447.

Full text
Abstract:
Artificial intelligence (AI) and machine learning (ML) present some application opportunities and challenges that can be framed as learning problems. The performance of machine learning models depends on algorithms and the data. Moreover, learning algorithms create a model of reality through learning and testing with data processes, and their performance shows an agreement degree of their assumed model with reality. ML algorithms have been successfully used in numerous classification problems. With the developing popularity of using ML models for many purposes in different domains, the validation of such predictive models is currently required more formally. Traditionally, there are many studies related to model evaluation, robustness, reliability, and the quality of the data and the data-driven models. However, those studies do not consider the concept of the applicability domain (AD) yet. The issue is that the AD is not often well defined, or it is not defined at all in many fields. This work investigates the robustness of ML classification models from the applicability domain perspective. A standard definition of applicability domain regards the spaces in which the model provides results with specific reliability. The main aim of this study is to investigate the connection between the applicability domain approach and the classification model performance. We are examining the usefulness of assessing the AD for the classification model, i.e. reliability, reuse, robustness of classifiers. The work is implemented using three approaches, and these approaches are conducted in three various attempts: firstly, assessing the applicability domain for the classification model; secondly, investigating the robustness of the classification model based on the applicability domain approach; thirdly, selecting an optimal model using Pareto optimality. The experiments in this work are illustrated by considering different machine learning algorithms for binary and multi-class classifications for healthcare datasets from public benchmark data repositories. In the first approach, the decision trees algorithm (DT) is used for the classification of data in the classification stage. The feature selection method is applied to choose features for classification. The obtained classifiers are used in the third approach for selection of models using Pareto optimality. The second approach is implemented using three steps; namely, building classification model; generating synthetic data; and evaluating the obtained results. The results obtained from the study provide an understanding of how the proposed approach can help to define the model’s robustness and the applicability domain, for providing reliable outputs. These approaches open opportunities for classification data and model management. The proposed algorithms are implemented through a set of experiments on classification accuracy of instances, which fall in the domain of the model. For the first approach, by considering all the features, the highest accuracy obtained is 0.98, with thresholds average of 0.34 for Breast cancer dataset. After applying recursive feature elimination (RFE) method, the accuracy is 0.96% with 0.27 thresholds average. For the robustness of the classification model based on the applicability domain approach, the minimum accuracy is 0.62% for Indian Liver Patient data at r=0.10, and the maximum accuracy is 0.99% for Thyroid dataset at r=0.10. For the selection of an optimal model using Pareto optimality, the optimally selected classifier gives the accuracy of 0.94% with 0.35 thresholds average. This research investigates critical aspects of the applicability domain as related to the robustness of classification ML algorithms. However, the performance of machine learning techniques depends on the degree of reliable predictions of the model. In the literature, the robustness of the ML model can be defined as the ability of the model to provide the testing error close to the training error. Moreover, the properties can describe the stability of the model performance when being tested on the new datasets. Concluding, this thesis introduced the concept of applicability domain for classifiers and tested the use of this concept with some case studies on health-related public benchmark datasets.
Ministry of Higher Education in Libya
APA, Harvard, Vancouver, ISO, and other styles
5

Cherief-Abdellatif, Badr-Eddine. "Contributions to the theoretical study of variational inference and robustness." Electronic Thesis or Diss., Institut polytechnique de Paris, 2020. http://www.theses.fr/2020IPPAG001.

Full text
Abstract:
Cette thèse de doctorat traite de l'inférence variationnelle et de la robustesse en statistique et en machine learning. Plus précisément, elle se concentre sur les propriétés statistiques des approximations variationnelles et sur la conception d'algorithmes efficaces pour les calculer de manière séquentielle, et étudie les estimateurs basés sur le Maximum Mean Discrepancy comme règles d'apprentissage qui sont robustes à la mauvaise spécification du modèle.Ces dernières années, l'inférence variationnelle a été largement étudiée du point de vue computationnel, cependant, la littérature n'a accordé que peu d'attention à ses propriétés théoriques jusqu'à très récemment. Dans cette thèse, nous étudions la consistence des approximations variationnelles dans divers modèles statistiques et les conditions qui assurent leur consistence. En particulier, nous abordons le cas des modèles de mélange et des réseaux de neurones profonds. Nous justifions également d'un point de vue théorique l'utilisation de la stratégie de maximisation de l'ELBO, un critère numérique qui est largement utilisé dans la communauté VB pour la sélection de modèle et dont l'efficacité a déjà été confirmée en pratique. En outre, l'inférence Bayésienne offre un cadre d'apprentissage en ligne attrayant pour analyser des données séquentielles, et offre des garanties de généralisation qui restent valables même en cas de mauvaise spécification des modèles et en présence d'adversaires. Malheureusement, l'inférence Bayésienne exacte est rarement tractable en pratique et des méthodes d'approximation sont généralement employées, mais ces méthodes préservent-elles les propriétés de généralisation de l'inférence Bayésienne ? Dans cette thèse, nous montrons que c'est effectivement le cas pour certains algorithmes d'inférence variationnelle (VI). Nous proposons de nouveaux algorithmes tempérés en ligne et nous en déduisons des bornes de généralisation. Notre résultat théorique repose sur la convexité de l'objectif variationnel, mais nous soutenons que notre résultat devrait être plus général et présentons des preuves empiriques à l'appui. Notre travail donne des justifications théoriques en faveur des algorithmes en ligne qui s'appuient sur des méthodes Bayésiennes approchées.Une autre question d'intérêt majeur en statistique qui est abordée dans cette thèse est la conception d'une procédure d'estimation universelle. Cette question est d'un intérêt majeur, notamment parce qu'elle conduit à des estimateurs robustes, un thème d'actualité en statistique et en machine learning. Nous abordons le problème de l'estimation universelle en utilisant un estimateur de minimisation de distance basé sur la Maximum Mean Discrepancy. Nous montrons que l'estimateur est robuste à la fois à la dépendance et à la présence de valeurs aberrantes dans le jeu de données. Nous mettons également en évidence les liens qui peuvent exister avec les estimateurs de minimisation de distance utilisant la distance L2. Enfin, nous présentons une étude théorique de l'algorithme de descente de gradient stochastique utilisé pour calculer l'estimateur, et nous étayons nos conclusions par des simulations numériques. Nous proposons également une version Bayésienne de notre estimateur, que nous étudions à la fois d'un point de vue théorique et d'un point de vue computationnel
This PhD thesis deals with variational inference and robustness. More precisely, it focuses on the statistical properties of variational approximations and the design of efficient algorithms for computing them in an online fashion, and investigates Maximum Mean Discrepancy based estimators as learning rules that are robust to model misspecification.In recent years, variational inference has been extensively studied from the computational viewpoint, but only little attention has been put in the literature towards theoretical properties of variational approximations until very recently. In this thesis, we investigate the consistency of variational approximations in various statistical models and the conditions that ensure the consistency of variational approximations. In particular, we tackle the special case of mixture models and deep neural networks. We also justify in theory the use of the ELBO maximization strategy, a model selection criterion that is widely used in the Variational Bayes community and is known to work well in practice.Moreover, Bayesian inference provides an attractive online-learning framework to analyze sequential data, and offers generalization guarantees which hold even under model mismatch and with adversaries. Unfortunately, exact Bayesian inference is rarely feasible in practice and approximation methods are usually employed, but do such methods preserve the generalization properties of Bayesian inference? In this thesis, we show that this is indeed the case for some variational inference algorithms. We propose new online, tempered variational algorithms and derive their generalization bounds. Our theoretical result relies on the convexity of the variational objective, but we argue that our result should hold more generally and present empirical evidence in support of this. Our work presents theoretical justifications in favor of online algorithms that rely on approximate Bayesian methods. Another point that is addressed in this thesis is the design of a universal estimation procedure. This question is of major interest, in particular because it leads to robust estimators, a very hot topic in statistics and machine learning. We tackle the problem of universal estimation using a minimum distance estimator based on the Maximum Mean Discrepancy. We show that the estimator is robust to both dependence and to the presence of outliers in the dataset. We also highlight the connections that may exist with minimum distance estimators using L2-distance. Finally, we provide a theoretical study of the stochastic gradient descent algorithm used to compute the estimator, and we support our findings with numerical simulations. We also propose a Bayesian version of our estimator, that we study from both a theoretical and a computational points of view
APA, Harvard, Vancouver, ISO, and other styles
6

Ilyas, Andrew. "On practical robustness of machine learning systems." Thesis, Massachusetts Institute of Technology, 2018. https://hdl.handle.net/1721.1/122911.

Full text
Abstract:
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2018
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 71-79).
We consider the importance of robustness in evaluating machine learning systems, an in particular systems involving deep learning. We consider these systems' vulnerability to adversarial examples--subtle, crafted perturbations to inputs which induce large change in output. We show that these adversarial examples are not only theoretical concern, by desigining the first 3D adversarial objects, and by demonstrating that these examples can be constructed even when malicious actors have little power. We suggest a potential avenue for building robust deep learning models by leveraging generative models.
by Andrew Ilyas.
M. Eng.
M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science
APA, Harvard, Vancouver, ISO, and other styles
7

Ishii, Shotaro, and David Ljunggren. "A Comparative Analysis of Robustness to Noise in Machine Learning Classifiers." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-302532.

Full text
Abstract:
Data that stems from real measurements often to some degree contain distortions. Such distortions are generally referred to as noise in machine learning terminology, and can lead to decreased classification accuracy and poor prediction results. In this study, three machine learning classifiers were compared by their performance and robustness in the presence of noise. More specifically, random forests, support vector machines and artificial neural networks were trained and compared on four different data sets with varying levels of noise artificially added to them. In summary, the random forest classifier performed the best and was the most robust classifier at eight out of ten of noise levels, closely followed by the artificial neural network classifier. At the two remaining noise levels, the support vector machine classifier with a linear kernel performed the best and was the most robust classifier.
Data som härstammar från verkliga mätningar innehåller ofta förvrängningar i viss utsträckning. Sådana förvrängningar kan i vissa fall leda till försämrad klassificeringsnoggrannhet. I den här studien jämförs tre klassificeringsalgoritmer med avseende på hur pass robusta de är när den data de presenteras innehåller syntetiska förvrängningar. Mer specifikt så tränades och jämfördes slumpskogar, stödvektormaskiner och artificiella neuronnät på fyra olika mängder data med varierande nivåer av syntetiska förvrängningar. Sammanfattningsvis så presterade slumpskogen bäst, och var den mest robusta klassificeringsalgoritmen på åtta av tio förvrängningsnivåer, tätt följt av det artificiella neuronnätet. På de två återstående förvrängningsnivåerna presterade stödvektormaskinen med linjär kärna bäst och var den mest robusta klassificeringsalgoritmen.
APA, Harvard, Vancouver, ISO, and other styles
8

Ebrahimi, Javid. "Robustness of Neural Networks for Discrete Input: An Adversarial Perspective." Thesis, University of Oregon, 2019. http://hdl.handle.net/1794/24535.

Full text
Abstract:
In the past few years, evaluating on adversarial examples has become a standard procedure to measure robustness of deep learning models. Literature on adversarial examples for neural nets has largely focused on image data, which are represented as points in continuous space. However, a vast proportion of machine learning models operate on discrete input, and thus demand a similar rigor in understanding their vulnerabilities and robustness. We study robustness of neural network architectures for textual and graph inputs, through the lens of adversarial input perturbations. We will cover methods for both attacks and defense; we will focus on 1) addressing challenges in optimization for creating adversarial perturbations for discrete data; 2) evaluating and contrasting white-box and black-box adversarial examples; and 3) proposing efficient methods to make the models robust against adversarial attacks.
APA, Harvard, Vancouver, ISO, and other styles
9

Fagogenis, Georgios. "Increasing the robustness of autonomous systems to hardware degradation using machine learning." Thesis, Heriot-Watt University, 2016. http://hdl.handle.net/10399/3378.

Full text
Abstract:
Autonomous systems perform predetermined tasks (missions) with minimum supervision. In most applications, the state of the world changes with time. Sensors are employed to measure part or whole of the world's state. However, sensors often fail amidst operation; feeding as such decision-making with wrong information about the world. Moreover, hardware degradation may alter dynamic behaviour, and subsequently the capabilities, of an autonomous system; rendering the original mission infeasible. This thesis applies machine learning to yield powerful and robust tools that can facilitate autonomy in modern systems. Incremental kernel regression is used for dynamic modelling. Algorithms of this sort are easy to train and are highly adaptive. Adaptivity allows for model adjustments, whenever the environment of operation changes. Bayesian reasoning provides a rigorous framework for addressing uncertainty. Moreover, using Bayesian Networks, complex inference regarding hardware degradation can be answered. Specifically, adaptive modelling is combined with Bayesian reasoning to yield recursive estimation algorithms that are robust to sensor failures. Two solutions are presented by extending existing recursive estimation algorithms from the robotics literature. The algorithms are deployed on an underwater vehicle and the performance is assessed in real-world experiments. A comparison against standard filters is also provided. Next, the previous algorithms are extended to consider sensor and actuator failures jointly. An algorithm that can detect thruster failures in an Autonomous Underwater Vehicle has been developed. Moreover, the algorithm adapts the dynamic model online to compensate for the detected fault. The performance of this algorithm was also tested in a real-world application. One step further than hardware fault detection, prognostics predict how much longer can a particular hardware component operate normally. Ubiquitous sensors in modern systems render data-driven prognostics a viable solution. However, training is based on skewed datasets; datasets where the samples from the faulty region of operation are much fewer than the ones from the healthy region of operation. This thesis presents a prognostic algorithm that tackles the problem of imbalanced (skewed) datasets.
APA, Harvard, Vancouver, ISO, and other styles
10

Haussamer, Nicolai Haussamer. "Model Calibration with Machine Learning." Master's thesis, University of Cape Town, 2018. http://hdl.handle.net/11427/29451.

Full text
Abstract:
This dissertation focuses on the application of neural networks to financial model calibration. It provides an introduction to the mathematics of basic neural networks and training algorithms. Two simplified experiments based on the Black-Scholes and constant elasticity of variance models are used to demonstrate the potential usefulness of neural networks in calibration. In addition, the main experiment features the calibration of the Heston model using model-generated data. In the experiment, we show that the calibrated model parameters reprice a set of options to a mean relative implied volatility error of less than one per cent. The limitations and shortcomings of neural networks in model calibration are also investigated and discussed.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Books on the topic "Machine Learning Model Robustness"

1

Mohamed, Khaled Salah. Machine Learning for Model Order Reduction. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-319-75714-8.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Subrahmanian, V. S., Chiara Pulice, James F. Brown, and Jacob Bonen-Clark. A Machine Learning Based Model of Boko Haram. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-60614-5.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Sturm, Jürgen. Approaches to Probabilistic Model Learning for Mobile Manipulation Robots. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
4

Widjanarko, Bambang. Pengembangan model model machine learning ketahanan pangan melalui pembentukan zona musim (ZOM) suatu wilayah: Laporan akhir hibah kompetitif penelitian sesuai prioritas nasional tahun I. Surabaya: Lembaga Penelitian dan Pengabdian Kepada Masyarakat, Institut Teknologi Sepuluh Nopember, 2010.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
5

Adversarial Robustness for Machine Learning Models. Elsevier Science & Technology Books, 2022.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
6

Adversarial Robustness for Machine Learning Models. Elsevier Science & Technology, 2022.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
7

Adversarial Robustness for Machine Learning. Elsevier, 2023. http://dx.doi.org/10.1016/c2020-0-01078-9.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Machine Learning Algorithms: Adversarial Robustness in Signal Processing. Springer International Publishing AG, 2022.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
9

Winn, John Michael. Model-Based Machine Learning. Taylor & Francis Group, 2021.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
10

Mohamed, Khaled Salah. Machine Learning for Model Order Reduction. Springer, 2019.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
More sources

Book chapters on the topic "Machine Learning Model Robustness"

1

Bunse, Mirko, and Katharina Morik. "Certification of Model Robustness in Active Class Selection." In Machine Learning and Knowledge Discovery in Databases. Research Track, 266–81. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-86520-7_17.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Guan, Ji, Wang Fang, and Mingsheng Ying. "Robustness Verification of Quantum Classifiers." In Computer Aided Verification, 151–74. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-81685-8_7.

Full text
Abstract:
AbstractSeveral important models of machine learning algorithms have been successfully generalized to the quantum world, with potential speedup to training classical classifiers and applications to data analytics in quantum physics that can be implemented on the near future quantum computers. However, quantum noise is a major obstacle to the practical implementation of quantum machine learning. In this work, we define a formal framework for the robustness verification and analysis of quantum machine learning algorithms against noises. A robust bound is derived and an algorithm is developed to check whether or not a quantum machine learning algorithm is robust with respect to quantum training data. In particular, this algorithm can find adversarial examples during checking. Our approach is implemented on Google’s TensorFlow Quantum and can verify the robustness of quantum machine learning algorithms with respect to a small disturbance of noises, derived from the surrounding environment. The effectiveness of our robust bound and algorithm is confirmed by the experimental results, including quantum bits classification as the “Hello World” example, quantum phase recognition and cluster excitation detection from real world intractable physical problems, and the classification of MNIST from the classical world.
APA, Harvard, Vancouver, ISO, and other styles
3

Bartz-Beielstein, Thomas, and Martin Zaefferer. "Models." In Hyperparameter Tuning for Machine and Deep Learning with R, 27–69. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-19-5170-1_3.

Full text
Abstract:
AbstractThis chapter presents a unique overview and a comprehensive explanation of Machine Learning (ML) and Deep Learning (DL) methods. Frequently used ML and DL methods; their hyperparameter configurations; and their features such as types, their sensitivity, and robustness, as well as heuristics for their determination, constraints, and possible interactions are presented. In particular, we cover the following methods: $$k$$ k -Nearest Neighbor (KNN), Elastic Net (EN), Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and DL. This chapter in itself might serve as a stand-alone handbook already. It contains years of experience in transferring theoretical knowledge into a practical guide.
APA, Harvard, Vancouver, ISO, and other styles
4

Mancino, Alberto Carlo Maria, and Tommaso Di Noia. "Towards Differentially Private Machine Learning Models and Their Robustness to Adversaries." In Lecture Notes in Computer Science, 455–61. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-09917-5_35.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Johnson, Patricia M., Geunu Jeong, Kerstin Hammernik, Jo Schlemper, Chen Qin, Jinming Duan, Daniel Rueckert, et al. "Evaluation of the Robustness of Learned MR Image Reconstruction to Systematic Deviations Between Training and Test Data for the Models from the fastMRI Challenge." In Machine Learning for Medical Image Reconstruction, 25–34. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-88552-6_3.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Lehrer, Steven F., Tian Xie, and Guanxi Yi. "Do the Hype of the Benefits from Using New Data Science Tools Extend to Forecasting Extremely Volatile Assets?" In Data Science for Economics and Finance, 287–330. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-66891-4_13.

Full text
Abstract:
AbstractThis chapter first provides an illustration of the benefits of using machine learning for forecasting relative to traditional econometric strategies. We consider the short-term volatility of the Bitcoin market by realized volatility observations. Our analysis highlights the importance of accounting for nonlinearities to explain the gains of machine learning algorithms and examines the robustness of our findings to the selection of hyperparameters. This provides an illustration of how different machine learning estimators improve the development of forecast models by relaxing the functional form assumptions that are made explicit when writing up an econometric model. Our second contribution is to illustrate how deep learning can be used to measure market-level sentiment from a 10% random sample of Twitter users. This sentiment variable significantly improves forecast accuracy for every econometric estimator and machine algorithm considered in our forecasting application. This provides an illustration of the benefits of new tools from the natural language processing literature at creating variables that can improve the accuracy of forecasting models.
APA, Harvard, Vancouver, ISO, and other styles
7

Han, Bo, Bo He, Mengmeng Ma, Tingting Sun, Tianhong Yan, and Amaury Lendasse. "RMSE-ELM: Recursive Model Based Selective Ensemble of Extreme Learning Machines for Robustness Improvement." In Proceedings of ELM-2014 Volume 1, 273–92. Cham: Springer International Publishing, 2015. http://dx.doi.org/10.1007/978-3-319-14063-6_24.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Conrad, F., E. Boos, M. Mälzer, H. Wiemer, and S. Ihlenfeldt. "Impact of Data Sampling on Performance and Robustness of Machine Learning Models in Production Engineering." In Lecture Notes in Production Engineering, 463–72. Cham: Springer International Publishing, 2023. http://dx.doi.org/10.1007/978-3-031-18318-8_47.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Deng, Lirui, Youjian Zhao, and Heng Bao. "A Self-supervised Adversarial Learning Approach for Network Intrusion Detection System." In Communications in Computer and Information Science, 73–85. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-8285-9_5.

Full text
Abstract:
AbstractThe network intrusion detection system (NIDS) plays an essential role in network security. Although many data-driven approaches from the field of machine learning have been proposed to increase the efficacy of NIDSs, it still suffers from extreme data imbalance and the performance of existing algorithms depends highly on training datasets. To counterpart the class-imbalanced problem in network intrusion detection, it is necessary for models to capture more representative clues within same categories instead of learning from only classification loss. In this paper, we proposed a self-supervised adversarial learning approach for intrusion detection, which utilize instance-level discrimination for better representation learning and employs a adversarial perturbation styled data augmentation to improve the robustness of NIDS on rarely seen attacking types. State-of-the-art result was achieved on multiple frequently-used datasets and experiment conducted on cross-dataset setting demonstrated good generalization ability.
APA, Harvard, Vancouver, ISO, and other styles
10

Labaca Castro, Raphael. "Towards Robustness." In Machine Learning under Malware Attack, 83–91. Wiesbaden: Springer Fachmedien Wiesbaden, 2023. http://dx.doi.org/10.1007/978-3-658-40442-0_11.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Machine Learning Model Robustness"

1

Zhou, Zhengbo, and Jianfei Yang. "Attentive Manifold Mixup for Model Robustness." In ICMLSC 2022: 2022 The 6th International Conference on Machine Learning and Soft Computing. New York, NY, USA: ACM, 2022. http://dx.doi.org/10.1145/3523150.3523164.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Sivaslioglu, Samed, Ferhat Ozgur Catak, and Ensar Gul. "Incrementing Adversarial Robustness with Autoencoding for Machine Learning Model Attacks." In 2019 27th Signal Processing and Communications Applications Conference (SIU). IEEE, 2019. http://dx.doi.org/10.1109/siu.2019.8806432.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Jeanselme, V., A. Wertz, G. Clermont, M. R. Pinsky, and A. Dubrawski. "Robustness of Machine Learning Models for Hemorrhage Detection." In American Thoracic Society 2020 International Conference, May 15-20, 2020 - Philadelphia, PA. American Thoracic Society, 2020. http://dx.doi.org/10.1164/ajrccm-conference.2020.201.1_meetingabstracts.a6320.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Izmailov, Rauf, Sridhar Venkatesan, Achyut Reddy, Ritu Chadha, Michael De Lucia, and Alina Oprea. "Poisoning attacks on machine learning models in cyber systems and mitigation strategies." In Security, Robustness, and Trust in Artificial Intelligence and Distributed Architectures, edited by Misty Blowers, Russell D. Hall, and Venkateswara R. Dasari. SPIE, 2022. http://dx.doi.org/10.1117/12.2622112.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Bharitkar, Sunil. "Generative Feature Models and Robustness Analysis for Multimedia Content Classification." In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). IEEE, 2019. http://dx.doi.org/10.1109/icmla.2019.00025.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Shi, Ziqiang, Chaoliang Zhong, Yasuto Yokota, Wensheng Xia, and Jun Sun. "Robustness Evaluation of Deep Learning Models Based on Local Prediction Consistency." In 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA). IEEE, 2019. http://dx.doi.org/10.1109/icmla.2019.00224.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Reshytko, A., D. Egorov, A. Klenitskiy, and A. Shchepetnov. "WellNet: improvement of machine learning models robustness via comprehensive multi oilfield dataset." In EAGE Subsurface Intelligence Workshop. European Association of Geoscientists & Engineers, 2019. http://dx.doi.org/10.3997/2214-4609.2019x610116.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Zhang, Yu-Nong, Zhen Li, Dong-Sheng Guo, Ke Chen, and Pei Chen. "Superior robustness of using power-sigmoid activation functions in Z-type models for time-varying problems solving." In 2013 International Conference on Machine Learning and Cybernetics (ICMLC). IEEE, 2013. http://dx.doi.org/10.1109/icmlc.2013.6890387.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Sun, Haotian, Wenxing Zhou, and Jidong Kang. "Development of a Near-Neutral pH Stress Corrosion Cracking Growth Model for Pipelines Using Machine Learning Algorithms." In 2022 14th International Pipeline Conference. American Society of Mechanical Engineers, 2022. http://dx.doi.org/10.1115/ipc2022-87207.

Full text
Abstract:
Abstract Near-neutral pH stress corrosion cracking (NNpHSCC) is one of the leading causes of failure for buried pipelines. Characterizing the NNpHSCC growth rate accurately remains a challenging task for the pipeline industry. In this study, an NNpHSCC growth model for buried pipelines is developed based on experimental data obtained from full-scale tests conducted at the CanmetMATERIALS of Natural Resources Canada of pipe specimens that are in contact with near-neutral pH environment and subjected to cyclic internal pressures. Four machine learning algorithms, namely the random forest (RF), extremely randomized trees (ET), gradient boosting (GB) and extreme gradient boosting (XGB), are employed to estimate the crack growth rates da/dN from input variables characterizing the pipe geometry, internal pressure and environmental condition. The machine learning models are trained through hyperparameter tuning and k-fold cross validation to improve the model robustness. Model performances are validated and compared using an independent test dataset. This study provides an initial step in using machine learning tools to develop robust NNpHSCC growth models suitable for practical applications.
APA, Harvard, Vancouver, ISO, and other styles
10

Albeanu, Grigore, and Alexandra stefania Moloiu. "LEARNING METHODS AND TRANSFERABLE APPROACHES." In eLSE 2021. ADL Romania, 2021. http://dx.doi.org/10.12753/2066-026x-21-082.

Full text
Abstract:
Learning to learn, an ability common to humans and animals, implies that the more knowledge is acquired, the better a new field can be investigated. Knowledge transfer is also a well known paradigm applied both for individuals and groups (networks). Mainly, the transfer of knowledge across individuals, groups and organizational units, is possible in our e-society, through repositories, e-learning platforms, social networks, specialized blogs, online courses etc. Self-learning, auto-didacticism, is based also on strong principles investigated by psychologists working for education. This is an opportunity to think of augmented intelligence: man-machine hybrid. Integrating human knowledge into machine learning portals will increase the robustness of machine learning, and provide explanations on selected decisions. In this paper we investigate a large plethora of learning approaches, self-learning models, domain adaptation techniques, and transferable approaches to machines in order to solve real life problems like detection, recognition,and understanding. The topics are common for people making use of emotional, behavioral, and cognitive self-regulation aspects. However, the machines have to learn more to discover the behavior of users, connected machines, and artificial messages received from an artificial environment. The transferred knowledge can be in the form of input data (signals), feature representations (extracted from signal), or model parameters (discovered through algorithms). Some concepts like self, non-self, convenient environment, sources of learning, adaptation to new domains, adaptation to new environments, and challenging transferable strategies are discussed in the first part. Some applications from the machine learning field are presented in the second part from the viewpoint of learning methods and transferable approaches.
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "Machine Learning Model Robustness"

1

Perdigão, Rui A. P. Information physics and quantum space technologies for natural hazard sensing, modelling and prediction. Meteoceanics, September 2021. http://dx.doi.org/10.46337/210930.

Full text
Abstract:
Disruptive socio-natural transformations and climatic change, where system invariants and symmetries break down, defy the traditional complexity paradigms such as machine learning and artificial intelligence. In order to overcome this, we introduced non-ergodic Information Physics, bringing physical meaning to inferential metrics, and a coevolving flexibility to the metrics of information transfer, resulting in new methods for causal discovery and attribution. With this in hand, we develop novel dynamic models and analysis algorithms natively built for quantum information technological platforms, expediting complex system computations and rigour. Moreover, we introduce novel quantum sensing technologies in our Meteoceanics satellite constellation, providing unprecedented spatiotemporal coverage, resolution and lead, whilst using exclusively sustainable materials and processes across the value chain. Our technologies bring out novel information physical fingerprints of extreme events, with recently proven records in capturing early warning signs for extreme hydro-meteorologic events and seismic events, and do so with unprecedented quantum-grade resolution, robustness, security, speed and fidelity in sensing, processing and communication. Our advances, from Earth to Space, further provide crucial predictive edge and added value to early warning systems of natural hazards and long-term predictions supporting climatic security and action.
APA, Harvard, Vancouver, ISO, and other styles
2

Rduner, Tim G. J., and Helen Toner. Key Concepts in AI Safety: Specification in Machine Learning. Center for Security and Emerging Technology, December 2021. http://dx.doi.org/10.51593/20210031.

Full text
Abstract:
This paper is the fourth installment in a series on “AI safety,” an area of machine learning research that aims to identify causes of unintended behavior in machine learning systems and develop tools to ensure these systems work safely and reliably. The first paper in the series, “Key Concepts in AI Safety: An Overview,” outlined three categories of AI safety issues—problems of robustness, assurance, and specification—and the subsequent two papers described problems of robustness and assurance, respectively. This paper introduces specification as a key element in designing modern machine learning systems that operate as intended.
APA, Harvard, Vancouver, ISO, and other styles
3

Rudner, Tim, and Helen Toner. Key Concepts in AI Safety: Interpretability in Machine Learning. Center for Security and Emerging Technology, March 2021. http://dx.doi.org/10.51593/20190042.

Full text
Abstract:
This paper is the third installment in a series on “AI safety,” an area of machine learning research that aims to identify causes of unintended behavior in machine learning systems and develop tools to ensure these systems work safely and reliably. The first paper in the series, “Key Concepts in AI Safety: An Overview,” described three categories of AI safety issues: problems of robustness, assurance, and specification. This paper introduces interpretability as a means to enable assurance in modern machine learning systems.
APA, Harvard, Vancouver, ISO, and other styles
4

Bajari, Patrick, Denis Nekipelov, Stephen Ryan, and Miaoyu Yang. Demand Estimation with Machine Learning and Model Combination. Cambridge, MA: National Bureau of Economic Research, February 2015. http://dx.doi.org/10.3386/w20955.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Mueller, Juliane, Charuleka Varadharajan, Erica Siirila-Woodburn, and Charles Koven. Machine Learning for Adaptive Model Refinement to Bridge Scales. Office of Scientific and Technical Information (OSTI), April 2021. http://dx.doi.org/10.2172/1769741.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Rudner, Tim, and Helen Toner. Key Concepts in AI Safety: Robustness and Adversarial Examples. Center for Security and Emerging Technology, March 2021. http://dx.doi.org/10.51593/20190041.

Full text
Abstract:
This paper is the second installment in a series on “AI safety,” an area of machine learning research that aims to identify causes of unintended behavior in machine learning systems and develop tools to ensure these systems work safely and reliably. The first paper in the series, “Key Concepts in AI Safety: An Overview,” described three categories of AI safety issues: problems of robustness, assurance, and specification. This paper introduces adversarial examples, a major challenge to robustness in modern machine learning systems.
APA, Harvard, Vancouver, ISO, and other styles
7

Hamann, Hendrik F. A Multi-scale, Multi-Model, Machine-Learning Solar Forecasting Technology. Office of Scientific and Technical Information (OSTI), May 2017. http://dx.doi.org/10.2172/1395344.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Geza, Mangistu, T. Tesfa, Liangping Li, and M. Qiao. Toward Hybrid Physics -Machine Learning to improve Land Surface Model predictions. Office of Scientific and Technical Information (OSTI), April 2021. http://dx.doi.org/10.2172/1769785.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Tebaldi, Claudia, Zhangshuan Hou, Abigail Snyder, and Kalyn Dorheim. Machine Learning for a-posteriori model-observed data fusion to enhance predictive value of ESM output. Office of Scientific and Technical Information (OSTI), April 2021. http://dx.doi.org/10.2172/1769740.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Tang, Jinyun, William Riley, Qing Zhu, and Trevor Keenan. Using machine learning and artificial intelligence to improve model-data integrated earth system model predictions of water and carbon cycle extremes. Office of Scientific and Technical Information (OSTI), April 2021. http://dx.doi.org/10.2172/1769794.

Full text
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Machine Learning Model Robustness' for particular source types:
Journal articles Dissertations / Theses Books
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography