اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدCan Offline Testing of Deep Neural Networks Replace Their Online Testing?
203
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
We distinguish two general modes of testing for Deep Neural Networks (DNNs): Offline testing where DNNs are tested as individual units based on test datasets obtained without involving the DNNs under test, and online testing where DNNs are embedded into a specific application environment and tested in a closed-loop mode in interaction with the application environment. Typically, DNNs are subjected to both types of testing during their development life cycle where offline testing is applied immediately after DNN training and online testing follows after offline testing and once a DNN is deployed within a specific application environment. In this paper, we study the relationship between offline and online testing. Our goal is to determine how offline testing and online testing differ or complement one another and if offline testing results can be used to help reduce the cost of online testing? Though these questions are generally relevant to all autonomous systems, we study them in the context of automated driving systems where, as study subjects, we use DNNs automating end-to-end controls of steering functions of self-driving vehicles. Our results show that offline testing is less effective than online testing as many safety violations identified by online testing could not be identified by offline testing, while large prediction errors generated by offline testing always led to severe safety violations detectable by online testing. Further, we cannot exploit offline testing results to reduce the cost of online testing in practice since we are not able to identify specific situations where offline testing could be as accurate as online testing in identifying safety requirement violations.
قيم البحث
اقرأ أيضاً
There is a growing body of research on developing testing techniques for Deep Neural Networks (DNN). We distinguish two general modes of testing for DNNs: Offline testing where DNNs are tested as individual units based on test datasets obtained indep
endently from the DNNs under test, and online testing where DNNs are embedded into a specific application and tested in a close-loop mode in interaction with the application environment. In addition, we identify two sources for generating test datasets for DNNs: Datasets obtained from real-life and datasets generated by simulators. While offline testing can be used with datasets obtained from either sources, online testing is largely confined to using simulators since online testing within real-life applications can be time-consuming, expensive and dangerous. In this paper, we study the following two important questions aiming to compare test datasets and testing modes for DNNs: First, can we use simulator-generated data as a reliable substitute to real-world data for the purpose of DNN testing? Second, how do online and offline testing results differ and complement each other? Though these questions are generally relevant to all autonomous systems, we study them in the context of automated driving systems where, as study subjects, we use DNNs automating end-to-end control of cars steering actuators. Our results show that simulator-generated datasets are able to yield DNN prediction errors that are similar to those obtained by testing DNNs with real-life datasets. Further, offline testing is more optimistic than online testing as many safety violations identified by online testing could not be identified by offline testing, while large prediction errors generated by offline testing always led to severe safety violations detectable by online testing.
Deep learning achieves remarkable performance on pattern recognition, but can be vulnerable to defects of some important properties such as robustness and security. This tutorial is based on a stream of research conducted since the summer of 2018 at
a few UK universities, including the University of Liverpool, University of Oxford, Queens University Belfast, University of Lancaster, University of Loughborough, and University of Exeter. The research aims to adapt software engineering methods, in particular software testing methods, to work with machine learning models. Software testing techniques have been successful in identifying software bugs, and helping software developers in validating the software they design and implement. It is for this reason that a few software testing techniques -- such as the MC/DC coverage metric -- have been mandated in industrial standards for safety critical systems, including the ISO26262 for automotive systems and the RTCA DO-178B/C for avionics systems. However, these techniques cannot be directly applied to machine learning models, because the latter are drastically different from traditional software, and their design follows a completely different development life-cycle. As the outcome of this thread of research, the team has developed a series of methods that adapt the software testing techniques to work with a few classes of machine learning models. The latter notably include convolutional neural networks, recurrent neural networks, and random forest. The tools developed from this research are now collected, and publicly released, in a GitHub repository: url{https://github.com/TrustAI/DeepConcolic}, with the BSD 3-Clause licence. This tutorial is to go through the major functionalities of the tools with a few running examples, to exhibit how the developed techniques work, what the results are, and how to interpret them.
Testing is an important activity in engineering of industrial software. For such software, testing is usually performed manually by handcrafting test suites based on specific design techniques and domain-specific experience. To support developers in
testing, different approaches for producing good test suites have been proposed. In the last couple of years combinatorial testing has been explored with the goal of automatically combining the input values of the software based on a certain strategy. Pairwise testing is a combinatorial technique used to generate test suites by varying the values of each pair of input parameters to a system until all possible combinations of those parameters are created. There is some evidence suggesting that these kinds of techniques are efficient and relatively good at detecting software faults. Unfortunately, there is little experimental evidence on the comparison of these combinatorial testing techniques with, what is perceived as, rigorous manually handcrafted testing. In this study we compare pairwise test suites with test suites created manually by engineers for 45 industrial programs. The test suites were evaluated in terms of fault detection, code coverage and number of tests. The results of this study show that pairwise testing, while useful for achieving high code coverage and fault detection for the majority of the programs, is almost as effective in terms of fault detection as manual testing. The results also suggest that pairwise testing is just as good as manual testing at fault detection for 64% of the programs.
The boom of DL technology leads to massive DL models built and shared, which facilitates the acquisition and reuse of DL models. For a given task, we encounter multiple DL models available with the same functionality, which are considered as candidat
es to achieve this task. Testers are expected to compare multiple DL models and select the more suitable ones w.r.t. the whole testing context. Due to the limitation of labeling effort, testers aim to select an efficient subset of samples to make an as precise rank estimation as possible for these models. To tackle this problem, we propose Sample Discrimination based Selection (SDS) to select efficient samples that could discriminate multiple models, i.e., the prediction behaviors (right/wrong) of these samples would be helpful to indicate the trend of model performance. To evaluate SDS, we conduct an extensive empirical study with three widely-used image datasets and 80 real world DL models. The experimental results show that, compared with state-of-the-art baseline methods, SDS is an effective and efficient sample selection method to rank multiple DL models.
Deep learning (DL) defines a new data-driven programming paradigm where the internal system logic is largely shaped by the training data. The standard way of evaluating DL models is to examine their performance on a test dataset. The quality of the t
est dataset is of great importance to gain confidence of the trained models. Using an inadequate test dataset, DL models that have achieved high test accuracy may still lack generality and robustness. In traditional software testing, mutation testing is a well-established technique for quality evaluation of test suites, which analyzes to what extent a test suite detects the injected faults. However, due to the fundamental difference between traditional software and deep learning-based software, traditional mutation testing techniques cannot be directly applied to DL systems. In this paper, we propose a mutation testing framework specialized for DL systems to measure the quality of test data. To do this, by sharing the same spirit of mutation testing in traditional software, we first define a set of source-level mutation operators to inject faults to the source of DL (i.e., training data and training programs). Then we design a set of model-level mutation operators that directly inject faults into DL models without a training process. Eventually, the quality of test data could be evaluated from the analysis on to what extent the injected faults could be detected. The usefulness of the proposed mutation testing techniques is demonstrated on two public datasets, namely MNIST and CIFAR-10, with three DL models.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
