The problem of all-relevant feature selection is concerned with finding a relevant feature set with preserved redundancies. There exist several approximations to solve this problem but only one could give a distinction between strong and weak relevance. This approach was limited to the case of linear problems. In this work, we present a new solution for this distinction in the non-linear case through the use of random forest models and statistical methods.
Deep learning techniques are currently the state of the art approach to deal with image classification problems. Nevertheless, non-expert users might find challenging the use of these techniques due to several reasons, including the lack of enough images, the necessity of trying different models and conducting a thorough comparison of the results obtained with them, and the technical difficulties of employing different libraries, tools and special purpose hardware like GPUs. In this work, we present FrImCla, an open-source and free tool that simplifies the construction of robust models for image classification from a dataset of images, and only using the computer CPU. Given a dataset of annotated images, FrImCla automatically constructs a classification model (both for single-label and multi-label classification problems) by trying several feature extractors (based both on transfer learning and traditional computer vision methods) and machine learning algorithms, and selecting the best combination after a thorough statistical analysis. Thus, this tool can be employed by non-expert users to create accurate models from small datasets of images without requiring any special purpose hardware. In addition, in this paper, we show that FrImCla can be employed to construct accurate models that are close, or even better, to the state-of-the-art models.
Material recognition can help inform robots about how to properly interact with and manipulate real-world objects. In this paper, we present a multimodal sensing technique, leveraging near-infrared spectroscopy and close-range high resolution texture imaging, that enables robots to estimate the materials of household objects. We release a dataset of high resolution texture images and spectral measurements collected from a mobile manipulator that interacted with 144 household objects. We then present a neural network architecture that learns a compact multimodal representation of spectral measurements and texture images. When generalizing material classification to new objects, we show that this multimodal representation enables a robot to recognize materials with greater performance as compared to prior state-of-the-art approaches. Finally, we present how a robot can combine this high resolution local sensing with images from the robot's head-mounted camera to achieve accurate material classification over a scene of objects on a table.
Image classification has been studied extensively but there has been limited work in the direction of using non-conventional, external guidance other than traditional image-label pairs to train such models. In this thesis we present a set of methods to leverage information about the semantic hierarchy induced by class labels. In the first part of the thesis, we inject label-hierarchy knowledge to an arbitrary classifier and empirically show that availability of such external semantic information in conjunction with the visual semantics from images boosts overall performance. Taking a step further in this direction, we model more explicitly the label-label and label-image interactions by using order-preserving embedding-based models, prevalent in natural language, and tailor them to the domain of computer vision to perform image classification. Although, contrasting in nature, both the CNN-classifiers injected with hierarchical information, and the embedding-based models outperform a hierarchy-agnostic model on the newly presented, real-world ETH Entomological Collection image dataset https://www.research-collection.ethz.ch/handle/20.500.11850/365379.
Machine learning-based multi-label medical text classifications can be used to enhance the understanding of the human body and aid the need for patient care. We present a broad study on clinical natural language processing techniques to maximise a feature representing text when predicting medical codes on patients with multi-morbidity. We present results of multi-label medical text classification problems with 18, 50 and 155 labels. We compare several variations to embeddings, text tagging, and pre-processing. For imbalanced data we show that labels which occur infrequently, benefit the most from additional features incorporated in embeddings. We also show that high dimensional embeddings pre-trained using health-related data present a significant improvement in a multi-label setting, similarly to the way they improve performance for binary classification. High dimensional embeddings from this research are made available for public use.
Classification models for the multivariate time series have gained significant importance in the research community, but not much research has been done on generating adversarial samples for these models. Such samples of adversaries could become a security concern. In this paper, we propose transforming the existing adversarial transformation network (ATN) on a distilled model to attack various multivariate time series classification models. The proposed attack on the classification model utilizes a distilled model as a surrogate that mimics the behavior of the attacked classical multivariate time series classification models. The proposed methodology is tested onto 1-Nearest Neighbor Dynamic Time Warping (1-NN DTW) and a Fully Convolutional Network (FCN), all of which are trained on 18 University of East Anglia (UEA) and University of California Riverside (UCR) datasets. We show both models were susceptible to attacks on all 18 datasets. To the best of our knowledge, adversarial attacks have only been conducted in the domain of univariate time series and have not been conducted on multivariate time series. such an attack on time series classification models has never been done before. Additionally, we recommend future researchers that develop time series classification models to incorporating adversarial data samples into their training data sets to improve resilience on adversarial samples and to consider model robustness as an evaluative metric.
Vulnerability detection and safety of smart contracts are of paramount importance because of their immutable nature. Symbolic tools like OYENTE and MAIAN are typically used for vulnerability prediction in smart contracts. As these tools are computationally expensive, they are typically used to detect vulnerabilities until some predefined invocation depth. These tools require more search time as the invocation depth increases. Since the number of smart contracts is increasing exponentially, it is difficult to analyze the contracts using these traditional tools. Recently a machine learning technique called Long Short Term Memory (LSTM) has been used for binary classification, i.e., to predict whether a smart contract is vulnerable or not. This technique requires nearly constant search time as the invocation depth increases. In the present article, we have shown a multi-class classification, where we classify a smart contract in Suicidal, Prodigal, Greedy, or Normal categories. We used Average Stochastic Gradient Descent Weight-Dropped LSTM (AWD-LSTM), which is a variant of LSTM, to perform classification. We reduced the class imbalance (a large number of normal contracts as compared to other categories) by considering only the distinct opcode combination for normal contracts. We have achieved a weighted average Fbeta score of 90.0%. Hence, such techniques can be used to analyze a large number of smart contracts and help to improve the security of these contracts.
Word embeddings and pre-trained language models allow to build rich representations of text and have enabled improvements across most NLP tasks. Unfortunately they are very expensive to train, and many small companies and research groups tend to use models that have been pre-trained and made available by third parties, rather than building their own. This is suboptimal as, for many languages, the models have been trained on smaller (or lower quality) corpora. In addition, monolingual pre-trained models for non-English languages are not always available. At best, models for those languages are included in multilingual versions, where each language shares the quota of substrings and parameters with the rest of the languages. This is particularly true for smaller languages such as Basque. In this paper we show that a number of monolingual models (FastText word embeddings, FLAIR and BERT language models) trained with larger Basque corpora produce much better results than publicly available versions in downstream NLP tasks, including topic classification, sentiment classification, PoS tagging and NER. This work sets a new state-of-the-art in those tasks for Basque. All benchmarks and models used in this work are publicly available.
Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this setting, networks suffer from catastrophic forgetting which refers to the drastic drop in performance on previous tasks. The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes. Embedding networks have the advantage that new classes can be naturally included into the network without adding new weights. Therefore, we study incremental learning for embedding networks. In addition, we propose a new method to estimate the drift, called semantic drift, of features and compensate for it without the need of any exemplars. We approximate the drift of previous tasks based on the drift that is experienced by current task data. We perform experiments on fine-grained datasets, CIFAR100 and ImageNet-Subset. We demonstrate that embedding networks suffer significantly less from catastrophic forgetting. We outperform existing methods which do not require exemplars and obtain competitive results compared to methods which store exemplars. Furthermore, we show that our proposed SDC when combined with existing methods to prevent forgetting consistently improves results.
In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue by augmenting less-frequent classes via translating samples (e.g., images) from more-frequent classes. This simple approach enables a classifier to learn more generalizable features of minority classes, by transferring and leveraging the diversity of the majority information. Our experimental results on a variety of class-imbalanced datasets show that the proposed method improves the generalization on minority classes significantly compared to other existing re-sampling or re-weighting methods. The performance of our method even surpasses those of previous state-of-the-art methods for the imbalanced classification.
Blind modulation classification is an important step to implement cognitive radio networks. The multiple-input multiple-output (MIMO) technique is widely used in military and civil communication systems. Due to the lack of prior information about channel parameters and the overlapping of signals in the MIMO systems, the traditional likelihood-based and feature-based approaches cannot be applied in these scenarios directly. Hence, in this paper, to resolve the problem of blind modulation classification in MIMO systems, the time-frequency analysis method based on the windowed short-time Fourier transform is used to analyse the time-frequency characteristics of time-domain modulated signals. Then the extracted time-frequency characteristics are converted into RGB spectrogram images, and the convolutional neural network based on transfer learning is applied to classify the modulation types according to the RGB spectrogram images. Finally, a decision fusion module is used to fuse the classification results of all the receive antennas. Through simulations, we analyse the classification performance at different signal-to-noise ratios (SNRs), the results indicate that, for the single-input single-output (SISO) network, our proposed scheme can achieve 92.37% and 99.12% average classification accuracy at SNRs of -4 dB and 10 dB, respectively. For the MIMO network, our scheme achieves 80.42% and 87.92% average classification accuracy at -4 dB and 10 dB, respectively. This outperforms the existing classification methods based on baseband signals.
The improvement in Information Technology has encouraged the use of Igbo in the creation of text such as resources and news articles online. Text similarity is of great importance in any text-based applications. This paper presents a comparative analysis of n-gram text representation on Igbo text document similarity. It adopted Euclidean similarity measure to determine the similarities between Igbo text documents represented with two word-based n-gram text representation (unigram and bigram) models. The evaluation of the similarity measure is based on the adopted text representation models. The model is designed with Object-Oriented Methodology and implemented with Python programming language with tools from Natural Language Toolkits (NLTK). The result shows that unigram represented text has highest distance values whereas bigram has the lowest corresponding distance values. The lower the distance value, the more similar the two documents and better the quality of the model when used for a task that requires similarity measure. The similarity of two documents increases as the distance value moves down to zero (0). Ideally, the result analyzed revealed that Igbo text document similarity measured on bigram represented text gives accurate similarity result. This will give better, effective and accurate result when used for tasks such as text classification, clustering and ranking on Igbo text.
These days deep neural networks are ubiquitously used in a wide range of tasks, from image classification and machine translation to face identification and self-driving cars. In many applications, a single model error can lead to devastating financial, reputational and even life-threatening consequences. Therefore, it is crucially important to correct model mistakes quickly as they appear. In this work, we investigate the problem of neural network editing $-$ how one can efficiently patch a mistake of the model on a particular sample, without influencing the model behavior on other samples. Namely, we propose Editable Training, a model-agnostic training technique that encourages fast editing of the trained model. We empirically demonstrate the effectiveness of this method on large-scale image classification and machine translation tasks.
Few-shot learning has attracted intensive research attention in recent years. Many methods have been proposed to generalize a model learned from provided base classes to novel classes, but no previous work studies how to select base classes, or even whether different base classes will result in different generalization performance of the learned model. In this paper, we utilize a simple yet effective measure, the Similarity Ratio, as an indicator for the generalization performance of a few-shot model. We then formulate the base class selection problem as a submodular optimization problem over Similarity Ratio. We further provide theoretical analysis on the optimization lower bound of different optimization methods, which could be used to identify the most appropriate algorithm for different experimental settings. The extensive experiments on ImageNet, Caltech256 and CUB-200-2011 demonstrate that our proposed method is effective in selecting a better base dataset.
The deployment of Machine Learning (ML) models is a difficult and time-consuming job that comprises a series of sequential and correlated tasks that go from the data pre-processing, and the design and extraction of features, to the choice of the ML algorithm and its parameterisation. The task is even more challenging considering that the design of features is in many cases problem specific, and thus requires domain-expertise. To overcome these limitations Automated Machine Learning (AutoML) methods seek to automate, with few or no human-intervention, the design of pipelines, i.e., automate the selection of the sequence of methods that have to be applied to the raw data. These methods have the potential to enable non-expert users to use ML, and provide expert users with solutions that they would unlikely consider. In particular, this paper describes AutoML-DSGE - a novel grammar-based framework that adapts Dynamic Structured Grammatical Evolution (DSGE) to the evolution of Scikit-Learn classification pipelines. The experimental results include comparing AutoML-DSGE to another grammar-based AutoML framework, Resilient ClassificationPipeline Evolution (RECIPE), and show that the average performance of the classification pipelines generated by AutoML-DSGE is always superior to the average performance of RECIPE; the differences are statistically significant in 3 out of the 10 used datasets.
Extreme multi-label classification (XMC) is the problem of finding the relevant labels for an input, from a very large universe of possible labels. We consider XMC in the setting where labels are available only for groups of samples - but not for individual ones. Current XMC approaches are not built for such multi-instance multi-label (MIML) training data, and MIML approaches do not scale to XMC sizes. We develop a new and scalable algorithm to impute individual-sample labels from the group labels; this can be paired with any existing XMC method to solve the aggregated label problem. We characterize the statistical properties of our algorithm under mild assumptions, and provide a new end-to-end framework for MIML as an extension. Experiments on both aggregated label XMC and MIML tasks show the advantages over existing approaches.
Cervical cancer is the second most prevalent cancer affecting women today. As the early detection of cervical carcinoma relies heavily upon screening and pre-clinical testing, digital cervicography has great potential as a primary or auxiliary screening tool, especially in low-resource regions due to its low cost and easy access. Although an automated cervical dysplasia detection system has been desirable, traditional fully-supervised training of such systems requires large amounts of annotated data which are often labor-intensive to collect. To alleviate the need for much manual annotation, we propose a novel graph convolutional network (GCN) based semi-supervised classification model that can be trained with fewer annotations. In existing GCNs, graphs are constructed with fixed features and can not be updated during the learning process. This limits their ability to exploit new features learned during graph convolution. In this paper, we propose a novel and more flexible GCN model with a feature encoder that adaptively updates the adjacency matrix during learning and demonstrate that this model design leads to improved performance. Our experimental results on a cervical dysplasia classification dataset show that the proposed framework outperforms previous methods under a semi-supervised setting, especially when the labeled samples are scarce.
Boosting is a well-known method for improving the accuracy of weak learners in machine learning. However, its theoretical generalization guarantee is missing in literature. In this paper, we propose an efficient boosting method with theoretical generalization guarantees for binary classification. Three key ingredients of the proposed boosting method are: a) the \textit{fully-corrective greedy} (FCG) update in the boosting procedure, b) a differentiable \textit{squared hinge} (also called \textit{truncated quadratic}) function as the loss function, and c) an efficient alternating direction method of multipliers (ADMM) algorithm for the associated FCG optimization. The used squared hinge loss not only inherits the robustness of the well-known hinge loss for classification with outliers, but also brings some benefits for computational implementation and theoretical justification. Under some sparseness assumption, we derive a fast learning rate of the order ${\cal O}((m/\log m)^{-1/4})$ for the proposed boosting method, which can be further improved to ${\cal O}((m/\log m)^{-1/2})$ if certain additional noise assumption is imposed, where $m$ is the size of sample set. Both derived learning rates are the best ones among the existing generalization results of boosting-type methods for classification. Moreover, an efficient early stopping scheme is provided for the proposed method. A series of toy simulations and real data experiments are conducted to verify the developed theories and demonstrate the effectiveness of the proposed method.
This paper presents an accurate and robust embedded motor-imagery brain-computer interface (MI-BCI). The proposed novel model, based on EEGNet, matches the requirements of memory footprint and computational resources of low-power microcontroller units (MCUs), such as the ARM Cortex-M family. Furthermore, the paper presents a set of methods, including temporal downsampling, channel selection, and narrowing of the classification window, to further scale down the model to relax memory requirements with negligible accuracy degradation. Experimental results on the Physionet EEG Motor Movement/Imagery Dataset show that standard EEGNet achieves 82.43%, 75.07%, and 65.07% classification accuracy on 2-, 3-, and 4-class MI tasks in global validation, outperforming the state-of-the-art (SoA) convolutional neural network (CNN) by 2.05%, 5.25%, and 5.48%. Our novel method further scales down the standard EEGNet at a negligible accuracy loss of 0.31% with 7.6x memory footprint reduction and a small accuracy loss of 2.51% with 15x reduction. The scaled models are deployed on a commercial Cortex-M4F MCU taking 101ms and consuming 4.28mJ per inference for operating the smallest model, and on a Cortex-M7 with 44ms and 18.1mJ per inference for the medium-sized model, enabling a fully autonomous, wearable, and accurate low-power BCI.
Recent advances in neural networks have made great progress in the hyperspectral image (HSI) classification. However, the overfitting effect, which is mainly caused by complicated model structure and small training set, remains a major concern. Reducing the complexity of the neural networks could prevent overfitting to some extent, but also declines the networks' ability to express more abstract features. Enlarging the training set is also difficult, for the high expense of acquisition and manual labeling. In this paper, we propose an abundance-based multi-HSI classification method. Firstly, we convert every HSI from the spectral domain to the abundance domain by a dataset-specific autoencoder. Secondly, the abundance representations from multiple HSIs are collected to form an enlarged dataset. Lastly, we train an abundance-based classifier and employ the classifier to predict over all the involved HSI datasets. Different from the spectra that are usually highly mixed, the abundance features are more representative in reduced dimension with less noise. This benefits the proposed method to employ simple classifiers and enlarged training data, and to expect less overfitting issues. The effectiveness of the proposed method is verified by the ablation study and the comparative experiments.