Sparse Bayesian Learning (SBL) constructs an extremely sparse probabilistic model with very competitive generalization. However, SBL needs to invert a big covariance matrix with complexity $O(M^3)$ (M: feature size) for updating the regularization priors, making it difficult for problems with high dimensional feature space or large data size. As it may easily suffer from the memory overflow issue in such problems. This paper addresses this issue with a newly proposed diagonal Quasi-Newton (DQN) method for SBL called DQN-SBL where the inversion of big covariance matrix is ignored so that the complexity is reduced to $O(M)$. The DQN-SBL is thoroughly evaluated for non linear and linear classifications with various benchmarks of different sizes. Experimental results verify that DQN-SBL receives competitive generalization with a very sparse model and scales well to large-scale problems.
The newly emerged transformer technology has a tremendous impact on NLP research. In the general English domain, transformer-based models have achieved state-of-the-art performances on various NLP benchmarks. In the clinical domain, researchers also have investigated transformer models for clinical applications. The goal of this study is to systematically explore three widely used transformer-based models (i.e., BERT, RoBERTa, and XLNet) for clinical relation extraction and develop an open-source package with clinical pre-trained transformer-based models to facilitate information extraction in the clinical domain. We developed a series of clinical RE models based on three transformer architectures, namely BERT, RoBERTa, and XLNet. We evaluated these models using 2 publicly available datasets from 2018 MADE1.0 and 2018 n2c2 challenges. We compared two classification strategies (binary vs. multi-class classification) and investigated two approaches to generate candidate relations in different experimental settings. In this study, we compared three transformer-based (BERT, RoBERTa, and XLNet) models for relation extraction. We demonstrated that the RoBERTa-clinical RE model achieved the best performance on the 2018 MADE1.0 dataset with an F1-score of 0.8958. On the 2018 n2c2 dataset, the XLNet-clinical model achieved the best F1-score of 0.9610. Our results indicated that the binary classification strategy consistently outperformed the multi-class classification strategy for clinical relation extraction. Our methods and models are publicly available at https://github.com/uf-hobi-informatics-lab/ClinicalTransformerRelationExtraction. We believe this work will improve current practice on clinical relation extraction and other related NLP tasks in the biomedical domain.
Convolutional Neural Networks (CNNs) have been dominating classification tasks in various domains, such as machine vision, machine listening, and natural language processing. In machine listening, while generally exhibiting very good generalization capabilities, CNNs are sensitive to the specific audio recording device used, which has been recognized as a substantial problem in the acoustic scene classification (DCASE) community. In this study, we investigate the relationship between over-parameterization of acoustic scene classification models, and their resulting generalization abilities. Specifically, we test scaling CNNs in width and depth, under different conditions. Our results indicate that increasing width improves generalization to unseen devices, even without an increase in the number of parameters.
Recently, semiconductors' demand has exploded in virtual reality, smartphones, wearable devices, the internet of things, robotics, and automobiles. Semiconductor manufacturers want to make semiconductors with high yields. To do this, manufacturers conduct many quality assurance activities. Wafer map pattern classification is a typical way of quality assurance. The defect pattern on the wafer map can tell us which process has a problem. Most of the existing wafer map classification methods are based on supervised methods. The supervised methods tend to have high performance, but they require extensive labor and expert knowledge to produce labeled datasets with a balanced distribution in mind. In the semiconductor manufacturing process, it is challenging to get defect data with balanced distribution. In this paper, we propose a one-class classification method using an Adversarial Autoencoder (AAE) with Deep Support Vector Data Description (DSVDD) prior, which generates random vectors within the hypersphere of DSVDD. We use the WM-811k dataset, which consists of a real-world wafer map. We compare the F1 score performance of our model with DSVDD and AAE.
Deep learning has played a major role in the interpretation of dermoscopic images for detecting skin defects and abnormalities. However, current deep learning solutions for dermatological lesion analysis are typically limited in providing probabilistic predictions which highlights the importance of concerning uncertainties. This concept of uncertainty can provide a confidence level for each feature which prevents overconfident predictions with poor generalization on unseen data. In this paper, we propose an overall framework that jointly considers dermatological classification and uncertainty estimation together. The estimated confidence of each feature to avoid uncertain feature and undesirable shift, which are caused by environmental difference of input image, in the latent space is pooled from confidence network. Our qualitative results show that modeling uncertainties not only helps to quantify model confidence for each prediction but also helps classification layers to focus on confident features, therefore, improving the accuracy for dermatological lesion classification. We demonstrate the potential of the proposed approach in two state-of-the-art dermoscopic datasets (ISIC 2018 and ISIC 2019).
Predictive uncertainties in classification tasks are often a consequence of model inadequacy or insufficient training data. In popular applications, such as image processing, we are often required to scrutinise these uncertainties by meaningfully attributing them to input features. This helps to improve interpretability assessments. However, there exist few effective frameworks for this purpose. Vanilla forms of popular methods for the provision of saliency masks, such as SHAP or integrated gradients, adapt poorly to target measures of uncertainty. Thus, state-of-the-art tools instead proceed by creating counterfactual or adversarial feature vectors, and assign attributions by direct comparison to original images. In this paper, we present a novel framework that combines path integrals, counterfactual explanations and generative models, in order to procure attributions that contain few observable artefacts or noise. We evidence that this outperforms existing alternatives through quantitative evaluations with popular benchmarking methods and data sets of varying complexity.
We demonstrate the feasibility of framing a classically learned deep neural network as an energy based model that can be processed on a one-step quantum annealer in order to exploit fast sampling times. We propose approaches to overcome two hurdles for high resolution image classification on a quantum processing unit (QPU): the required number and binary nature of the model states. With this novel method we successfully transfer a convolutional neural network to the QPU and show the potential for classification speedup of at least one order of magnitude.
The current standard for a variety of computer vision tasks using smaller numbers of labelled training examples is to fine-tune from weights pre-trained on a large image classification dataset such as ImageNet. The application of transfer learning and transfer learning methods tends to be rigidly binary. A model is either pre-trained or not pre-trained. Pre-training a model either increases performance or decreases it, the latter being defined as negative transfer. Application of L2-SP regularisation that decays the weights towards their pre-trained values is either applied or all weights are decayed towards 0. This paper re-examines these assumptions. Our recommendations are based on extensive empirical evaluation that demonstrate the application of a non-binary approach to achieve optimal results. (1) Achieving best performance on each individual dataset requires careful adjustment of various transfer learning hyperparameters not usually considered, including number of layers to transfer, different learning rates for different layers and different combinations of L2SP and L2 regularization. (2) Best practice can be achieved using a number of measures of how well the pre-trained weights fit the target dataset to guide optimal hyperparameters. We present methods for non-binary transfer learning including combining L2SP and L2 regularization and performing non-traditional fine-tuning hyperparameter searches. Finally we suggest heuristics for determining the optimal transfer learning hyperparameters. The benefits of using a non-binary approach are supported by final results that come close to or exceed state of the art performance on a variety of tasks that have traditionally been more difficult for transfer learning.
In this paper, we present an overview of Nearest neighbor (NN) methods, which are frequently employed for solving classification problems using supervised learning. The article concisely introduces the theoretical background, algorithmic, and implementation aspects along with the key applications. From an application standpoint, this article explores the challenges related to the 5G and beyond wireless networks which can be solved using NN classification techniques.
We present a novel learning-based approach to graph representations of road networks employing state-of-the-art graph convolutional neural networks. Our approach is applied to realistic road networks of 17 cities from Open Street Map. While edge features are crucial to generate descriptive graph representations of road networks, graph convolutional networks usually rely on node features only. We show that the highly representative edge features can still be integrated into such networks by applying a line graph transformation. We also propose a method for neighborhood sampling based on a topological neighborhood composed of both local and global neighbors. We compare the performance of learning representations using different types of neighborhood aggregation functions in transductive and inductive tasks and in supervised and unsupervised learning. Furthermore, we propose a novel aggregation approach, Graph Attention Isomorphism Network, GAIN. Our results show that GAIN outperforms state-of-the-art methods on the road type classification problem.
Graph classification is crucial in network analyses. Networks face potential security threats, such as adversarial attacks. Some defense methods may trade off the algorithm complexity for robustness, such as adversarial training, whereas others may trade off clean example performance, such as smoothingbased defense. Most suffer from high complexity or low transferability. To address this problem, we proposed EGC2, an enhanced graph classification model with easy graph compression. EGC2 captures the relationship between the features of different nodes by constructing feature graphs and improving the aggregation of the node-level representations. To achieve lower-complexity defense applied to graph classification models, EGC2 utilizes a centrality-based edge-importance index to compress the graphs, filtering out trivial structures and adversarial perturbations in the input graphs, thus improving the model's robustness. Experiments on ten benchmark datasets demonstrate that the proposed feature read-out and graph compression mechanisms enhance the robustness of multiple basic models, resulting in a state-of-the-art performance in terms of accuracy and robustness against various adversarial attacks.
In recent years, deep learning has made brilliant achievements in Environmental Microorganism (EM) image classification. However, image classification of small EM datasets has still not obtained good research results. Therefore, researchers need to spend a lot of time searching for models with good classification performance and suitable for the current equipment working environment. To provide reliable references for researchers, we conduct a series of comparison experiments on 21 deep learning models. The experiment includes direct classification, imbalanced training, and hyperparameter tuning experiments. During the experiments, we find complementarities among the 21 models, which is the basis for feature fusion related experiments. We also find that the data augmentation method of geometric deformation is difficult to improve the performance of VTs (ViT, DeiT, BotNet and T2T-ViT) series models. In terms of model performance, Xception has the best classification performance, the ViT model consumes the least time for training, and the ShuffleNet-V2 model has the least number of parameters.
Active learning is a state-of-art machine learning approach to deal with an abundance of unlabeled data. In the field of Natural Language Processing, typically it is costly and time-consuming to have all the data annotated. This inefficiency inspires out our application of active learning in text classification. Traditional unsupervised k-means clustering is first modified into a semi-supervised version in this research. Then, a novel attempt is applied to further extend the algorithm into active learning scenario with Penalized Min-Max-selection, so as to make limited queries that yield more stable initial centroids. This method utilizes both the interactive query results from users and the underlying distance representation. After tested on a Chinese news dataset, it shows a consistent increase in accuracy while lowering the cost in training.
Recently, various deep neural networks have been applied to classify electroencephalogram (EEG) signal. EEG is a brain signal that can be acquired in a non-invasive way and has a high temporal resolution. It can be used to decode the intention of users. As the EEG signal has a high dimension of feature space, appropriate feature extraction methods are needed to improve classification performance. In this study, we obtained spatio-temporal feature representation and classified them with the combined convolutional neural networks (CNN)-gated recurrent unit (GRU) model. To this end, we obtained covariance matrices in each different temporal band and then concatenated them on the temporal axis to obtain a final spatio-temporal feature representation. In the classification model, CNN is responsible for spatial feature extraction and GRU is responsible for temporal feature extraction. Classification performance was improved by distinguishing spatial data processing and temporal data processing. The average accuracy of the proposed model was 77.70% for the BCI competition IV_2a data set. The proposed method outperformed all other methods compared as a baseline method.
Inertial sensor-based human activity recognition (HAR) is the base of many human-centered mobile applications. Deep learning-based fine-grained HAR models enable accurate classification in various complex application scenarios. Nevertheless, the large storage and computational overhead of the existing fine-grained deep HAR models hinder their widespread deployment on resource-limited platforms. Inspired by the knowledge distillation's reasonable model compression and potential performance improvement capability, we design a multi-level HAR modeling pipeline called Stage-Logits-Memory Distillation (SMLDist) based on the widely-used MobileNet. By paying more attention to the frequency-related features during the distillation process, the SMLDist improves the HAR classification robustness of the students. We also propose an auto-search mechanism in the heterogeneous classifiers to improve classification performance. Extensive simulation results demonstrate that SMLDist outperforms various state-of-the-art HAR frameworks in accuracy and F1 macro score. The practical evaluation of the Jetson Xavier AGX platform shows that the SMLDist model is both energy-efficient and computation-efficient. These experiments validate the reasonable balance between the robustness and efficiency of the proposed model. The comparative experiments of knowledge distillation on six public datasets also demonstrate that the SMLDist outperforms other advanced knowledge distillation methods of students' performance, which verifies the good generalization of the SMLDist on other classification tasks, including but not limited to HAR.
Deep neural networks have significantly contributed to the success in predictive accuracy for classification tasks. However, they tend to make over-confident predictions in real-world settings, where domain shifting and out-of-distribution (OOD) examples exist. Most research on uncertainty estimation focuses on computer vision because it provides visual validation on uncertainty quality. However, few have been presented in the natural language process domain. Unlike Bayesian methods that indirectly infer uncertainty through weight uncertainties, current evidential uncertainty-based methods explicitly model the uncertainty of class probabilities through subjective opinions. They further consider inherent uncertainty in data with different root causes, vacuity (i.e., uncertainty due to a lack of evidence) and dissonance (i.e., uncertainty due to conflicting evidence). In our paper, we firstly apply evidential uncertainty in OOD detection for text classification tasks. We propose an inexpensive framework that adopts both auxiliary outliers and pseudo off-manifold samples to train the model with prior knowledge of a certain class, which has high vacuity for OOD samples. Extensive empirical experiments demonstrate that our model based on evidential uncertainty outperforms other counterparts for detecting OOD examples. Our approach can be easily deployed to traditional recurrent neural networks and fine-tuned pre-trained transformers.
One of the most promising approaches for data analysis and exploration of large data sets is Machine Learning techniques that are inspired by brain models. Such methods use alternative learning rules potentially more efficiently than established learning rules. In this work, we focus on the potential of brain-inspired ML for exploiting High-Performance Computing (HPC) resources to solve ML problems: we discuss the BCPNN and an HPC implementation, called StreamBrain, its computational cost, suitability to HPC systems. As an example, we use StreamBrain to analyze the Higgs Boson dataset from High Energy Physics and discriminate between background and signal classes in collisions of high-energy particle colliders. Overall, we reach up to 69.15% accuracy and 76.4% Area Under the Curve (AUC) performance.
Cartoon face recognition is challenging as they typically have smooth color regions and emphasized edges, the key to recognize cartoon faces is to precisely perceive their sparse and critical shape patterns. However, it is quite difficult to learn a shape-oriented representation for cartoon face recognition with convolutional neural networks (CNNs). To mitigate this issue, we propose the GraphJigsaw that constructs jigsaw puzzles at various stages in the classification network and solves the puzzles with the graph convolutional network (GCN) in a progressive manner. Solving the puzzles requires the model to spot the shape patterns of the cartoon faces as the texture information is quite limited. The key idea of GraphJigsaw is constructing a jigsaw puzzle by randomly shuffling the intermediate convolutional feature maps in the spatial dimension and exploiting the GCN to reason and recover the correct layout of the jigsaw fragments in a self-supervised manner. The proposed GraphJigsaw avoids training the classification model with the deconstructed images that would introduce noisy patterns and are harmful for the final classification. Specially, GraphJigsaw can be incorporated at various stages in a top-down manner within the classification model, which facilitates propagating the learned shape patterns gradually. GraphJigsaw does not rely on any extra manual annotation during the training process and incorporates no extra computation burden at inference time. Both quantitative and qualitative experimental results have verified the feasibility of our proposed GraphJigsaw, which consistently outperforms other face recognition or jigsaw-based methods on two popular cartoon face datasets with considerable improvements.
This paper presents a deep learning approach for the classification of Engineering (CAD) models using Convolutional Neural Networks (CNNs). Owing to the availability of large annotated datasets and also enough computational power in the form of GPUs, many deep learning-based solutions for object classification have been proposed of late, especially in the domain of images and graphical models. Nevertheless, very few solutions have been proposed for the task of functional classification of CAD models. Hence, for this research, CAD models have been collected from Engineering Shape Benchmark (ESB), National Design Repository (NDR) and augmented with newer models created using a modelling software to form a dataset - 'CADNET'. It is proposed to use a residual network architecture for CADNET, inspired by the popular ResNet. A weighted Light Field Descriptor (LFD) scheme is chosen as the method of feature extraction, and the generated images are fed as inputs to the CNN. The problem of class imbalance in the dataset is addressed using a class weights approach. Experiments have been conducted with other signatures such as geodesic distance etc. using deep networks as well as other network architectures on the CADNET. The LFD-based CNN approach using the proposed network architecture, along with gradient boosting yielded the best classification accuracy on CADNET.
The developmental process of embryos follows a monotonic order. An embryo can progressively cleave from one cell to multiple cells and finally transform to morula and blastocyst. For time-lapse videos of embryos, most existing developmental stage classification methods conduct per-frame predictions using an image frame at each time step. However, classification using only images suffers from overlapping between cells and imbalance between stages. Temporal information can be valuable in addressing this problem by capturing movements between neighboring frames. In this work, we propose a two-stream model for developmental stage classification. Unlike previous methods, our two-stream model accepts both temporal and image information. We develop a linear-chain conditional random field (CRF) on top of neural network features extracted from the temporal and image streams to make use of both modalities. The linear-chain CRF formulation enables tractable training of global sequential models over multiple frames while also making it possible to inject monotonic development order constraints into the learning process explicitly. We demonstrate our algorithm on two time-lapse embryo video datasets: i) mouse and ii) human embryo datasets. Our method achieves 98.1 % and 80.6 % for mouse and human embryo stage classification, respectively. Our approach will enable more profound clinical and biological studies and suggests a new direction for developmental stage classification by utilizing temporal information.