Though neural network models demonstrate impressive performance, we do not understand exactly how these black-box models make individual predictions. This drawback has led to substantial research devoted to understand these models in areas such as robustness, interpretability, and generalization ability. In this paper, we consider the problem of exploring the prediction level sets of a classifier using probabilistic programming. We define a prediction level set to be the set of examples for which the predictor has the same specified prediction confidence with respect to some arbitrary data distribution. Notably, our sampling-based method does not require the classifier to be differentiable, making it compatible with arbitrary classifiers. As a specific instantiation, if we take the classifier to be a neural network and the data distribution to be that of the training data, we can obtain examples that will result in specified predictions by the neural network. We demonstrate this technique with experiments on a synthetic dataset and MNIST. Such level sets in classification may facilitate human understanding of classification behaviors.
The challenge of automatically determining the correctness of test executions is referred to as the test oracle problem and is one of the key remaining issues for automated testing. The goal in this paper is to solve the test oracle problem in a way that is general, scalable and accurate. To achieve this, we use supervised learning over test execution traces. We label a small fraction of the execution traces with their verdict of pass or fail. We use the labelled traces to train a neural network (NN) model to learn to distinguish runtime patterns for passing versus failing executions for a given program. Our approach for building this NN model involves the following steps, 1. Instrument the program to record execution traces as sequences of method invocations and global state, 2. Label a small fraction of the execution traces with their verdicts, 3. Designing a NN component that embeds information in execution traces to fixed length vectors, 4. Design a NN model that uses the trace information for classification, 5. Evaluate the inferred classification model on unseen execution traces from the program. We evaluate our approach using case studies from different application domains: 1. Module from Ethereum Blockchain, 2. Module from PyTorch deep learning framework, 3. Microsoft SEAL encryption library components, 4. Sed stream editor, 5. Value pointer library and 6. Nine network protocols from Linux packet identifier, L7-Filter. We found the classification models for all subject programs resulted in high precision, recall and specificity, over 95%, while only training with an average 9% of the total traces. Our experiments show that the proposed neural network model is highly effective as a test oracle and is able to learn runtime patterns to distinguish passing and failing test executions for systems and tests from different application domains.
This paper proposes an improved version of the current online learning algorithm for a general fuzzy min-max neural network (GFMM) to tackle existing issues concerning expansion and contraction steps as well as the way of dealing with unseen data located on decision boundaries. These drawbacks lower its classification performance, so an improved algorithm is proposed in this study to address the above limitations. The proposed approach does not use the contraction process for overlapping hyperboxes, which is more likely to increase the error rate as shown in the literature. The empirical results indicated the improvement in the classification accuracy and stability of the proposed method compared to the original version and other fuzzy min-max classifiers. In order to reduce the sensitivity to the training samples presentation order of this new on-line learning algorithm, a simple ensemble method is also proposed.
In the last years, image classification processes like neural networks in the area of art-history and Heritage Informatics have experienced a broad distribution (Lang and Ommer 2018). These methods face several challenges, including the handling of comparatively small amounts of data as well as high-dimensional data in the Digital Humanities. Here, a Convolutional Neural Network (CNN) is used that output is not, as usual, a series of flat text labels but a series of semantically loaded vectors. These vectors result from a Distributional Semantic Model (DSM) which is generated from an in-domain text corpus. ----- In den letzten Jahren hat die Verwendung von Bildklassifizierungsverfahren wie neuronalen Netzwerken auch im Bereich der historischen Bildwissenschaften und der Heritage Informatics weite Verbreitung gefunden (Lang und Ommer 2018). Diese Verfahren stehen dabei vor einer Reihe von Herausforderungen, darunter dem Umgangmit den vergleichsweise kleinen Datenmengen sowie zugleich hochdimensionalen Da-tenr\"aumen in den digitalen Geisteswissenschaften. Meist bilden diese Methoden dieKlassifizierung auf einen vergleichsweise flachen Raum ab. Dieser flache Zugang verliert im Bem\"uhen um ontologische Eindeutigkeit eine Reihe von relevanten Dimensionen, darunter taxonomische, mereologische und assoziative Beziehungen zwischenden Klassen beziehungsweise dem nicht formalisierten Kontext. Dabei wird ein Convolutional Neural Network (CNN) genutzt, dessen Ausgabe im Trainingsprozess, anders als herk\"ommlich, nicht auf einer Serie flacher Textlabel beruht, sondern auf einer Serie von Vektoren. Diese Vektoren resultieren aus einem Distributional Semantic Model (DSM), welches aus einem Dom\"ane-Textkorpus generiert wird.
Fine-grained software vulnerability detection is an important and challenging problem. Ideally, a detection system (or detector) not only should be able to detect whether or not a program contains vulnerabilities, but also should be able to pinpoint the type of a vulnerability in question. Existing vulnerability detection methods based on deep learning can detect the presence of vulnerabilities (i.e., addressing the binary classification or detection problem), but cannot pinpoint types of vulnerabilities (i.e., incapable of addressing multiclass classification). In this paper, we propose the first deep learning-based system for multiclass vulnerability detection, dubbed $\mu$VulDeePecker. The key insight underlying $\mu$VulDeePecker is the concept of code attention, which can capture information that can help pinpoint types of vulnerabilities, even when the samples are small. For this purpose, we create a dataset from scratch and use it to evaluate the effectiveness of $\mu$VulDeePecker. Experimental results show that $\mu$VulDeePecker is effective for multiclass vulnerability detection and that accommodating control-dependence (other than data-dependence) can lead to higher detection capabilities.
Already before systems malfunction one has to know if hardware components will fail in near future in order to counteract in time. Thus, unplanned downtime is ought to be avoided. In medical imaging, maximizing the system's uptime is crucial for patients' health and healthcare provider's daily business. We aim to predict failures of Head/Neck coils used in Magnetic Resonance Imaging (MRI) by training a statistical model on sequential data collected over time. As image features depend on the coil's condition, their deviations from the normal range already hint to future failure. Thus, we used image features and their variation over time to predict coil damage. After comparison of different time series classification methods we found Long Short Term Memorys (LSTMs) to achieve the highest F-score of 86.43% and to tell with 98.33% accuracy if hardware should be replaced.
Target-oriented opinion words extraction (TOWE) is a new subtask of ABSA, which aims to extract the corresponding opinion words for a given opinion target in a sentence. Recently, neural network methods have been applied to this task and achieve promising results. However, the difficulty of annotation causes the datasets of TOWE to be insufficient, which heavily limits the performance of neural models. By contrast, abundant review sentiment classification data are easily available at online review sites. These reviews contain substantial latent opinions information and semantic patterns. In this paper, we propose a novel model to transfer these opinions knowledge from resource-rich review sentiment classification datasets to low-resource task TOWE. To address the challenges in the transfer process, we design an effective transformation method to obtain latent opinions, then integrate them into TOWE. Extensive experimental results show that our model achieves better performance compared to other state-of-the-art methods and significantly outperforms the base model without transferring opinions knowledge. Further analysis validates the effectiveness of our model.
The wide adoption of machine learning in the critical domains such as medical diagnosis, law, education had propelled the need for interpretable techniques due to the need for end users to understand the reasoning behind decisions due to learning systems. The computational intractability of interpretable learning led practitioners to design heuristic techniques, which fail to provide sound handles to tradeoff accuracy and interpretability. Motivated by the success of MaxSAT solvers over the past decade, recently MaxSAT-based approach, called MLIC, was proposed that seeks to reduce the problem of learning interpretable rules expressed in Conjunctive Normal Form (CNF) to a MaxSAT query. While MLIC was shown to achieve accuracy similar to that of other state of the art black-box classifiers while generating small interpretable CNF formulas, the runtime performance of MLIC is significantly lagging and renders approach unusable in practice. In this context, authors raised the question: Is it possible to achieve the best of both worlds, i.e., a sound framework for interpretable learning that can take advantage of MaxSAT solvers while scaling to real-world instances? In this paper, we take a step towards answering the above question in affirmation. We propose IMLI: an incremental approach to MaxSAT based framework that achieves scalable runtime performance via partition-based training methodology. Extensive experiments on benchmarks arising from UCI repository demonstrate that IMLI achieves up to three orders of magnitude runtime improvement without loss of accuracy and interpretability.
The goal of this work is to build a classifier that can identify text complexity within the context of teaching reading to English as a Second Language (ESL) learners. To present language learners with texts that are suitable to their level of English, a set of features that can describe the phonological, morphological, lexical, syntactic, discursive, and psychological complexity of a given text were identified. Using a corpus of 6171 texts, which had already been classified into three different levels of difficulty by ESL experts, different experiments were conducted with five machine learning algorithms. The results showed that the adopted linguistic features provide a good overall classification performance (F-Score = 0.97). A scalability evaluation was conducted to test if such a classifier could be used within real applications, where it can be, for example, plugged into a search engine or a web-scraping module. In this evaluation, the texts in the test set are not only different from those from the training set but also of different types (ESL texts vs. children reading texts). Although the overall performance of the classifier decreased significantly (F-Score = 0.65), the confusion matrix shows that most of the classification errors are between the classes two and three (the middle-level classes) and that the system has a robust performance in categorizing texts of class one and four. This behavior can be explained by the difference in classification criteria between the two corpora. Hence, the observed results confirm the usability of such a classifier within a real-world application.
Deep learning is playing a vital role in every field which involves data. It has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using traditional machine learning techniques in the past. In this study we focused on classification of protein sequences with deep learning techniques. The study of amino acid sequence is vital in life sciences. We used different word embedding techniques from Natural Language processing to represent the amino acid sequence as vectors. Our main goal was to classify sequences to four group of classes, that are DNA, RNA, Protein and hybrid. After several tests we have achieved almost 99% of train and test accuracy. We have experimented on CNN, LSTM, Bidirectional LSTM, and GRU.
The combination of neural network and fuzzy systems into neuro-fuzzy systems integrates fuzzy reasoning rules into the connectionist networks. However, the existing neuro-fuzzy systems are developed under shallow structures having lower generalization capacity. We propose the first end-to-end deep neuro-fuzzy network and investigate its application for image classification. Two new operations are developed based on definitions of Takagi-Sugeno-Kang (TSK) fuzzy model namely fuzzy inference operation and fuzzy pooling operations; stacks of these operations comprise the layers in this network. We evaluate the network on MNIST, CIFAR-10 and CIFAR-100 datasets, finding that the network has a reasonable accuracy in these benchmarks.
Although a large number of optimization algorithms have been proposed for black box optimization problems, the no free lunch theorems inform us that no algorithm can beat others on all types of problems. Different types of optimization problems need different optimization algorithms. To deal with this issue, researchers propose algorithm selection to suggest the best optimization algorithm from the algorithm set for a given unknown optimization problem. Usually, algorithm selection is treated as a classification or regression task. Deep learning, which has been shown to perform well on various classification and regression tasks, is applied to the algorithm selection problem in this paper. Our deep learning architecture is based on convolutional neural network and follows the main architecture of visual geometry group. This architecture has been applied to many different types of 2-D data. Moreover, we also propose a novel method to extract landscape information from the optimization problems and save the information as 2-D images. In the experimental section, we conduct three experiments to investigate the classification and optimization capability of our approach on the BBOB functions. The results indicate that our new approach can effectively solve the algorithm selection problem.
Spiking Neural Networks (SNNs) are brain-inspired, event-driven machine learning algorithms that have been widely recognized in producing ultra-high-energy-efficient hardware. Among existing SNNs, unsupervised SNNs based on synaptic plasticity, especially Spike-Timing-Dependent Plasticity (STDP), are considered to have great potential in imitating the learning process of the biological brain. Nevertheless, the existing STDP-based SNNs have limitations in constrained learning capability and/or slow learning speed. Most STDP-based SNNs adopted a slow-learning Fully-Connected (FC) architecture and used a sub-optimal vote-based scheme for spike decoding. In this paper, we overcome these limitations with: 1) a design of high-parallelism network architecture, inspired by the Inception module in Artificial Neural Networks (ANNs); 2) use of a Vote-for-All (VFA) decoding layer as a replacement to the standard vote-based spike decoding scheme, to reduce the information loss in spike decoding and, 3) a proposed adaptive repolarization (resetting) mechanism that accelerates SNNs' learning by enhancing spiking activities. Our experimental results on two established benchmark datasets (MNIST/EMNIST) show that our network architecture resulted in superior performance compared to the widely used FC architecture and a more advanced Locally-Connected (LC) architecture, and that our SNN achieved competitive results with state-of-the-art unsupervised SNNs (95.64%/80.11% accuracy on the MNIST/EMNISE dataset) while having superior learning efficiency and robustness against hardware damage. Our SNN achieved great classification accuracy with only hundreds of training iterations, and random destruction of large numbers of synapses or neurons only led to negligible performance degradation.
We propose a new method for cancer subtype classification from histopathological images, which can automatically detect tumor-specific features in a given whole slide image (WSI). The cancer subtype should be classified by referring to a WSI, i.e., a large-sized image (typically 40,000x40,000 pixels) of an entire pathological tissue slide, which consists of cancer and non-cancer portions. One difficulty arises from the high cost associated with annotating tumor regions in WSIs. Furthermore, both global and local image features must be extracted from the WSI by changing the magnifications of the image. In addition, the image features should be stably detected against the differences of staining conditions among the hospitals/specimens. In this paper, we develop a new CNN-based cancer subtype classification method by effectively combining multiple-instance, domain adversarial, and multi-scale learning frameworks in order to overcome these practical difficulties. When the proposed method was applied to malignant lymphoma subtype classifications of 196 cases collected from multiple hospitals, the classification performance was significantly better than the standard CNN or other conventional methods, and the accuracy compared favorably with that of standard pathologists.
We consider radar classifications of Activities of Daily Living (ADL) which can prove beneficial in fall detection, analysis of daily routines, and discerning physical and cognitive human conditions. We focus on contiguous motion classifications which follow and commensurate with the human ethogram of possible motion sequences. Contiguous motions can be closely connected with no clear time gap separations. In the proposed motion classification approach, we utilize the Radon transform applied to the radar range-map to detect the translation motion, whereas an energy detector is used to provide the onset and offset times of in-place motions, such as sitting down and standing up. It is shown that motion classifications give different results when performed forward and backward in time. The number of classes, thereby classification rates, considered by a classifier, is made variable depending on the current motion state and the possible transitioning activities in and out of the state. Motion examples are provided to delineate the performance of the proposed approach under typical sequences of human motions.
In real-world scenarios, data tends to exhibit a long-tailed distribution, which increases the difficulty of training deep networks. In this paper, we propose a novel self-paced knowledge distillation framework, termed Learning From Multiple Experts (LFME). Our method is inspired by the observation that networks trained on less imbalanced subsets of the distribution often yield better performances than their jointly-trained counterparts. We refer to these models as 'Experts', and the proposed LFME framework aggregates the knowledge from multiple 'Experts' to learn a unified student model. Specifically, the proposed framework involves two levels of adaptive learning schedules: Self-paced Expert Selection and Curriculum Instance Selection, so that the knowledge is adaptively transferred to the 'Student'. We conduct extensive experiments and demonstrate that our method is able to achieve superior performances compared to state-of-the-art methods. We also show that our method can be easily plugged into state-of-the-art long-tailed classification algorithms for further improvements.
The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from optical imaging. Given a large-scale SAR land cover dataset collected from TerraSAR-X images with a hierarchical three-level annotation of 150 categories and comprising more than 100,000 patches, three main challenges in automatically interpreting SAR images of highly imbalanced classes, geographic diversity, and label noise are addressed. In this letter, a deep transfer learning method is proposed based on a similarly annotated optical land cover dataset (NWPU-RESISC45). Besides, a top-2 smooth loss function with cost-sensitive parameters was introduced to tackle the label noise and imbalanced classes' problems. The proposed method shows high efficiency in transferring information from a similarly annotated remote sensing dataset, a robust performance on highly imbalanced classes, and is alleviating the over-fitting problem caused by label noise. What's more, the learned deep model has a good generalization for other SAR-specific tasks, such as MSTAR target recognition with a state-of-the-art classification accuracy of 99.46%.
In next-generation communications, massive machine-type communications (mMTC) induce severe burden on base stations. To address such an issue, automatic modulation classification (AMC) can help to reduce signaling overhead by blindly recognizing the modulation types without handshaking. Thus, it plays an important role in future intelligent modems. The emerging deep learning (DL) technique stores intelligence in the network, resulting in superior performance over traditional approaches. However, conventional DL-based approaches suffer from heavy training overhead, memory overhead, and computational complexity, which severely hinder practical applications for resource-limited scenarios, such as Vehicle-to-Everything (V2X) applications. Furthermore, the overhead of online retraining under time-varying fading channels has not been studied in the prior arts. In this work, an accumulated polar feature-based DL with a channel compensation mechanism is proposed to cope with the aforementioned issues. Firstly, the simulation results show that learning features from the polar domain with historical data information can approach near-optimal performance while reducing training overhead by 99.8 times. Secondly, the proposed neural network-based channel estimator (NN-CE) can learn the channel response and compensate for the distorted channel with 13% improvement. Moreover, in applying this lightweight NN-CE in a time-varying fading channel, two efficient mechanisms of online retraining are proposed, which can reduce transmission overhead and retraining overhead by 90% and 76%, respectively. Finally, the performance of the proposed approach is evaluated and compared with prior arts on a public dataset to demonstrate its great efficiency and lightness.
Researchers have proposed various activation functions. These activation functions help the deep network to learn non-linear behavior with a significant effect on training dynamics and task performance. The performance of these activations also depends on the initial state of the weight parameters, i.e., different initial state leads to a difference in the performance of a network. In this paper, we have proposed a cooperative initialization for training the deep network using ReLU activation function to improve the network performance. Our approach uses multiple activation functions in the initial few epochs for the update of all sets of weight parameters while training the network. These activation functions cooperate to overcome their drawbacks in the update of weight parameters, which in effect learn better "feature representation" and boost the network performance later. Cooperative initialization based training also helps in reducing the overfitting problem and does not increase the number of parameters, inference (test) time in the final model while improving the performance. Experiments show that our approach outperforms various baselines and, at the same time, performs well over various tasks such as classification and detection. The Top-1 classification accuracy of the model trained using our approach improves by 2.8% for VGG-16 and 2.1% for ResNet-56 on CIFAR-100 dataset.
Chronic obstructive pulmonary disease (COPD) is a lung disease that is not fully reversible and one of the leading causes of morbidity and mortality in the world. Early detection and diagnosis of COPD can increase the survival rate and reduce the risk of COPD progression in patients. Currently, the primary examination tool to diagnose COPD is spirometry. However, computed tomography (CT) is used for detecting symptoms and sub-type classification of COPD. Using different imaging modalities is a difficult and tedious task even for physicians and is subjective to inter-and intra-observer variations. Hence, developing meth-ods that can automatically classify COPD versus healthy patients is of great interest. In this paper, we propose a 3D deep learning approach to classify COPD and emphysema using volume-wise annotations only. We also demonstrate the impact of transfer learning on the classification of emphysema using knowledge transfer from a pre-trained COPD classification model.