LIVIVO - The Search Portal for Life Sciences

zur deutschen Oberfläche wechseln
Advanced search

Search results

Result 1 - 10 of total 33

Search options

  1. Book ; Online: On the Design of Deep Priors for Unsupervised Audio Restoration

    Narayanaswamy, Vivek Sivaraman / Thiagarajan, Jayaraman J. / Spanias, Andreas

    2021  

    Abstract: Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain. In this context, lot of recent ... ...

    Abstract Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain. In this context, lot of recent success has been achieved with sophisticated convolutional network constructions that recover audio signals in the spectral domain. However, in practice, audio priors require careful engineering of the convolutional kernels to be effective at solving ill-posed restoration tasks, while also being easy to train. To this end, in this paper, we propose a new U-Net based prior that does not impact either the network complexity or convergence behavior of existing convolutional architectures, yet leads to significantly improved restoration. In particular, we advocate the use of carefully designed dilation schedules and dense connections in the U-Net architecture to obtain powerful audio priors. Using empirical studies on standard benchmarks and a variety of ill-posed restoration tasks, such as audio denoising, in-painting and source separation, we demonstrate that our proposed approach consistently outperforms widely adopted audio prior architectures.
    Keywords Computer Science - Sound ; Computer Science - Machine Learning ; Electrical Engineering and Systems Science - Audio and Speech Processing
    Subject code 006
    Publishing date 2021-04-14
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  2. Article ; Online: DDxNet: a deep learning model for automatic interpretation of electronic health records, electrocardiograms and electroencephalograms.

    Thiagarajan, Jayaraman J / Rajan, Deepta / Katoch, Sameeksha / Spanias, Andreas

    Scientific reports

    2020  Volume 10, Issue 1, Page(s) 16428

    Abstract: Effective patient care mandates rapid, yet accurate, diagnosis. With the abundance of non-invasive diagnostic measurements and electronic health records (EHR), manual interpretation for differential diagnosis has become time-consuming and challenging. ... ...

    Abstract Effective patient care mandates rapid, yet accurate, diagnosis. With the abundance of non-invasive diagnostic measurements and electronic health records (EHR), manual interpretation for differential diagnosis has become time-consuming and challenging. This has led to wide-spread adoption of AI-powered tools, in pursuit of improving accuracy and efficiency of this process. While the unique challenges presented by each modality and clinical task demand customized tools, the cumbersome process of making problem-specific choices has triggered the critical need for a generic solution to enable rapid development of models in practice. In this spirit, we develop DDxNet, a deep architecture for time-varying clinical data, which we demonstrate to be well-suited for diagnostic tasks involving different modalities (ECG/EEG/EHR), required level of characterization (abnormality detection/phenotyping) and data fidelity (single-lead ECG/22-channel EEG). Using multiple benchmark problems, we show that DDxNet produces high-fidelity predictive models, and sometimes even provides significant performance gains over problem-specific solutions.
    MeSH term(s) Algorithms ; Deep Learning ; Electrocardiography/methods ; Electroencephalography/methods ; Electronic Health Records ; Humans ; Machine Learning ; Models, Theoretical ; Patient Care/methods ; Software
    Language English
    Publishing date 2020-10-02
    Publishing country England
    Document type Journal Article ; Research Support, Non-U.S. Gov't ; Research Support, U.S. Gov't, Non-P.H.S.
    ZDB-ID 2615211-3
    ISSN 2045-2322 ; 2045-2322
    ISSN (online) 2045-2322
    ISSN 2045-2322
    DOI 10.1038/s41598-020-73126-9
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  3. Article ; Online: Coverage-Based Designs Improve Sample Mining and Hyperparameter Optimization.

    Muniraju, Gowtham / Kailkhura, Bhavya / Thiagarajan, Jayaraman J / Bremer, Peer-Timo / Tepedelenlioglu, Cihan / Spanias, Andreas

    IEEE transactions on neural networks and learning systems

    2021  Volume 32, Issue 3, Page(s) 1241–1253

    Abstract: Sampling one or more effective solutions from large search spaces is a recurring idea in machine learning (ML), and sequential optimization has become a popular solution. Typical examples include data summarization, sample mining for predictive modeling, ...

    Abstract Sampling one or more effective solutions from large search spaces is a recurring idea in machine learning (ML), and sequential optimization has become a popular solution. Typical examples include data summarization, sample mining for predictive modeling, and hyperparameter optimization. Existing solutions attempt to adaptively trade off between global exploration and local exploitation, in which the initial exploratory sample is critical to their success. While discrepancy-based samples have become the de facto approach for exploration, results from computer graphics suggest that coverage-based designs, e.g., Poisson disk sampling, can be a superior alternative. In order to successfully adopt coverage-based sample designs to ML applications, which were originally developed for 2-D image analysis, we propose fundamental advances by constructing a parameterized family of designs with provably improved coverage characteristics and developing algorithms for effective sample synthesis. Using experiments in sample mining and hyperparameter optimization for supervised learning, we show that our approach consistently outperforms the existing exploratory sampling methods in both blind exploration and sequential search with Bayesian optimization.
    Language English
    Publishing date 2021-03-01
    Publishing country United States
    Document type Journal Article
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2020.2982936
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  4. Book ; Online: Using Deep Image Priors to Generate Counterfactual Explanations

    Narayanaswamy, Vivek / Thiagarajan, Jayaraman J. / Spanias, Andreas

    2020  

    Abstract: Through the use of carefully tailored convolutional neural network architectures, a deep image prior (DIP) can be used to obtain pre-images from latent representation encodings. Though DIP inversion has been known to be superior to conventional ... ...

    Abstract Through the use of carefully tailored convolutional neural network architectures, a deep image prior (DIP) can be used to obtain pre-images from latent representation encodings. Though DIP inversion has been known to be superior to conventional regularized inversion strategies such as total variation, such an over-parameterized generator is able to effectively reconstruct even images that are not in the original data distribution. This limitation makes it challenging to utilize such priors for tasks such as counterfactual reasoning, wherein the goal is to generate small, interpretable changes to an image that systematically leads to changes in the model prediction. To this end, we propose a novel regularization strategy based on an auxiliary loss estimator jointly trained with the predictor, which efficiently guides the prior to recover natural pre-images. Our empirical studies with a real-world ISIC skin lesion detection problem clearly evidence the effectiveness of the proposed approach in synthesizing meaningful counterfactuals. In comparison, we find that the standard DIP inversion often proposes visually imperceptible perturbations to irrelevant parts of the image, thus providing no additional insights into the model behavior.
    Keywords Computer Science - Machine Learning ; Computer Science - Computer Vision and Pattern Recognition
    Subject code 006
    Publishing date 2020-10-22
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  5. Book ; Online: Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks

    Shanthamallu, Uday Shankar / Thiagarajan, Jayaraman J. / Spanias, Andreas

    2020  

    Abstract: Graph Neural Networks (GNNs), a generalization of neural networks to graph-structured data, are often implemented using message passes between entities of a graph. While GNNs are effective for node classification, link prediction and graph classification, ...

    Abstract Graph Neural Networks (GNNs), a generalization of neural networks to graph-structured data, are often implemented using message passes between entities of a graph. While GNNs are effective for node classification, link prediction and graph classification, they are vulnerable to adversarial attacks, i.e., a small perturbation to the structure can lead to a non-trivial performance degradation. In this work, we propose Uncertainty Matching GNN (UM-GNN), that is aimed at improving the robustness of GNN models, particularly against poisoning attacks to the graph structure, by leveraging epistemic uncertainties from the message passing framework. More specifically, we propose to build a surrogate predictor that does not directly access the graph structure, but systematically extracts reliable knowledge from a standard GNN through a novel uncertainty-matching strategy. Interestingly, this uncoupling makes UM-GNN immune to evasion attacks by design, and achieves significantly improved robustness against poisoning attacks. Using empirical studies with standard benchmarks and a suite of global and target attacks, we demonstrate the effectiveness of UM-GNN, when compared to existing baselines including the state-of-the-art robust GCN.
    Keywords Statistics - Machine Learning ; Computer Science - Cryptography and Security ; Computer Science - Machine Learning
    Subject code 006
    Publishing date 2020-09-30
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  6. Book ; Online: Loss Estimators Improve Model Generalization

    Narayanaswamy, Vivek / Thiagarajan, Jayaraman J. / Rajan, Deepta / Spanias, Andreas

    2021  

    Abstract: With increased interest in adopting AI methods for clinical diagnosis, a vital step towards safe deployment of such tools is to ensure that the models not only produce accurate predictions but also do not generalize to data regimes where the training ... ...

    Abstract With increased interest in adopting AI methods for clinical diagnosis, a vital step towards safe deployment of such tools is to ensure that the models not only produce accurate predictions but also do not generalize to data regimes where the training data provide no meaningful evidence. Existing approaches for ensuring the distribution of model predictions to be similar to that of the true distribution rely on explicit uncertainty estimators that are inherently hard to calibrate. In this paper, we propose to train a loss estimator alongside the predictive model, using a contrastive training objective, to directly estimate the prediction uncertainties. Interestingly, we find that, in addition to producing well-calibrated uncertainties, this approach improves the generalization behavior of the predictor. Using a dermatology use-case, we show the impact of loss estimators on model generalization, in terms of both its fidelity on in-distribution data and its ability to detect out of distribution samples or new classes unseen during training.
    Keywords Computer Science - Machine Learning ; Statistics - Machine Learning
    Subject code 310
    Publishing date 2021-03-05
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  7. Book ; Online: Know Your Space

    Narayanaswamy, Vivek / Mubarka, Yamen / Anirudh, Rushil / Rajan, Deepta / Spanias, Andreas / Thiagarajan, Jayaraman J.

    Inlier and Outlier Construction for Calibrating Medical OOD Detectors

    2022  

    Abstract: We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors, in order to enable safe deployment of medical image classifiers. Motivated by the difficulty of curating suitable calibration datasets, synthetic augmentations have ...

    Abstract We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors, in order to enable safe deployment of medical image classifiers. Motivated by the difficulty of curating suitable calibration datasets, synthetic augmentations have become highly prevalent for inlier/outlier specification. While there have been rapid advances in data augmentation techniques, this paper makes a striking finding that the space in which the inliers and outliers are synthesized, in addition to the type of augmentation, plays a critical role in calibrating OOD detectors. Using the popular energy-based OOD detection framework, we find that the optimal protocol is to synthesize latent-space inliers along with diverse pixel-space outliers. Based on empirical studies with multiple medical imaging benchmarks, we demonstrate that our approach consistently leads to superior OOD detection ($15\% - 35\%$ in AUROC) over the state-of-the-art in a variety of open-set recognition settings.
    Keywords Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Machine Learning
    Subject code 006
    Publishing date 2022-07-11
    Publishing country us
    Document type Book ; Online
    Database BASE - Bielefeld Academic Search Engine (life sciences selection)

    Full text online

    More links

    Kategorien

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  8. Article ; Online: Articulation constrained learning with application to speech emotion recognition.

    Shah, Mohit / Tu, Ming / Berisha, Visar / Chakrabarti, Chaitali / Spanias, Andreas

    EURASIP journal on audio, speech, and music processing

    2019  Volume 2019

    Abstract: Speech emotion recognition methods combining articulatory information with acoustic features have been previously shown to improve recognition performance. Collection of articulatory data on a large scale may not be feasible in many scenarios, thus ... ...

    Abstract Speech emotion recognition methods combining articulatory information with acoustic features have been previously shown to improve recognition performance. Collection of articulatory data on a large scale may not be feasible in many scenarios, thus restricting the scope and applicability of such methods. In this paper, a discriminative learning method for emotion recognition using both articulatory and acoustic information is proposed. A traditional
    Language English
    Publishing date 2019-08-20
    Publishing country Germany
    Document type Journal Article
    ZDB-ID 2252877-5
    ISSN 1687-4722 ; 1687-4714
    ISSN (online) 1687-4722
    ISSN 1687-4714
    DOI 10.1186/s13636-019-0157-9
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

  9. Article ; Online: GrAMME: Semisupervised Learning Using Multilayered Graph Attention Models.

    Shanthamallu, Uday Shankar / Thiagarajan, Jayaraman J / Song, Huan / Spanias, Andreas

    IEEE transactions on neural networks and learning systems

    2019  Volume 31, Issue 10, Page(s) 3977–3988

    Abstract: Modern data analysis pipelines are becoming increasingly complex due to the presence of multiview information sources. While graphs are effective in modeling complex relationships, in many scenarios, a single graph is rarely sufficient to succinctly ... ...

    Abstract Modern data analysis pipelines are becoming increasingly complex due to the presence of multiview information sources. While graphs are effective in modeling complex relationships, in many scenarios, a single graph is rarely sufficient to succinctly represent all interactions, and hence, multilayered graphs have become popular. Though this leads to richer representations, extending solutions from the single-graph case is not straightforward. Consequently, there is a strong need for novel solutions to solve classical problems, such as node classification, in the multilayered case. In this article, we consider the problem of semisupervised learning with multilayered graphs. Though deep network embeddings, e.g., DeepWalk, are widely adopted for community discovery, we argue that feature learning with random node attributes, using graph neural networks, can be more effective. To this end, we propose to use attention models for effective feature learning and develop two novel architectures, GrAMME-SG and GrAMME-Fusion, that exploit the interlayer dependences for building multilayered graph embeddings. Using empirical studies on several benchmark data sets, we evaluate the proposed approaches and demonstrate significant performance improvements in comparison with the state-of-the-art network embedding strategies. The results also show that using simple random features is an effective choice, even in cases where explicit node attributes are not available.
    Language English
    Publishing date 2019-11-14
    Publishing country United States
    Document type Journal Article
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2019.2948797
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

  10. Article ; Online: Optimizing Kernel Machines Using Deep Learning.

    Song, Huan / J Thiagarajan, Jayaraman / Sattigeri, Prasanna / Spanias, Andreas

    IEEE transactions on neural networks and learning systems

    2018  Volume 29, Issue 11, Page(s) 5528–5540

    Abstract: Building highly nonlinear and nonparametric models is central to several state-of-the-art machine learning systems. Kernel methods form an important class of techniques that induce a reproducing kernel Hilbert space (RKHS) for inferring non-linear models ...

    Abstract Building highly nonlinear and nonparametric models is central to several state-of-the-art machine learning systems. Kernel methods form an important class of techniques that induce a reproducing kernel Hilbert space (RKHS) for inferring non-linear models through the construction of similarity functions from data. These methods are particularly preferred in cases where the training data sizes are limited and when prior knowledge of the data similarities is available. Despite their usefulness, they are limited by the computational complexity and their inability to support end-to-end learning with a task-specific objective. On the other hand, deep neural networks have become the de facto solution for end-to-end inference in several learning paradigms. In this paper, we explore the idea of using deep architectures to perform kernel machine optimization, for both computational efficiency and end-to-end inferencing. To this end, we develop the deep kernel machine optimization framework, that creates an ensemble of dense embeddings using Nyström kernel approximations and utilizes deep learning to generate task-specific representations through the fusion of the embeddings. Intuitively, the filters of the network are trained to fuse information from an ensemble of linear subspaces in the RKHS. Furthermore, we introduce the kernel dropout regularization to enable improved training convergence. Finally, we extend this framework to the multiple kernel case, by coupling a global fusion layer with pretrained deep kernel machines for each of the constituent kernels. Using case studies with limited training data, and lack of explicit feature sources, we demonstrate the effectiveness of our framework over conventional model inferencing techniques.
    Language English
    Publishing date 2018-03-06
    Publishing country United States
    Document type Journal Article ; Research Support, Non-U.S. Gov't ; Research Support, U.S. Gov't, Non-P.H.S.
    ISSN 2162-2388
    ISSN (online) 2162-2388
    DOI 10.1109/TNNLS.2018.2804895
    Database MEDical Literature Analysis and Retrieval System OnLINE

    More links

    Kategorien

    Order via subito

    This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

    Inter-library loan at ZB MED

    Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top