Ändra sökning
Avgränsa sökresultatet
1 - 15 av 15
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Träffar per sida
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sortering
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
  • Standard (Relevans)
  • Författare A-Ö
  • Författare Ö-A
  • Titel A-Ö
  • Titel Ö-A
  • Publikationstyp A-Ö
  • Publikationstyp Ö-A
  • Äldst först
  • Nyast först
  • Skapad (Äldst först)
  • Skapad (Nyast först)
  • Senast uppdaterad (Äldst först)
  • Senast uppdaterad (Nyast först)
  • Disputationsdatum (tidigaste först)
  • Disputationsdatum (senaste först)
Markera
Maxantalet träffar du kan exportera från sökgränssnittet är 250. Vid större uttag använd dig av utsökningar.
  • 1.
    Aghazadeh, Omid
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Azizpour, Hossein
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Carlsson, Stefan
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Mixture component identification and learning for visual recognition2012Ingår i: Computer Vision – ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part VI, Springer, 2012, s. 115-128Konferensbidrag (Refereegranskat)
    Abstract [en]

    The non-linear decision boundary between object and background classes - due to large intra-class variations - needs to be modelled by any classifier wishing to achieve good results. While a mixture of linear classifiers is capable of modelling this non-linearity, learning this mixture from weakly annotated data is non-trivial and is the paper's focus. Our approach is to identify the modes in the distribution of our positive examples by clustering, and to utilize this clustering in a latent SVM formulation to learn the mixture model. The clustering relies on a robust measure of visual similarity which suppresses uninformative clutter by using a novel representation based on the exemplar SVM. This subtle clustering of the data leads to learning better mixture models, as is demonstrated via extensive evaluations on Pascal VOC 2007. The final classifier, using a HOG representation of the global image patch, achieves performance comparable to the state-of-the-art while being more efficient at detection time.

  • 2.
    Azizpour, Hossein
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Visual Representations and Models: From Latent SVM to Deep Learning2016Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
    Abstract [en]

    Two important components of a visual recognition system are representation and model. Both involves the selection and learning of the features that are indicative for recognition and discarding those features that are uninformative. This thesis, in its general form, proposes different techniques within the frameworks of two learning systems for representation and modeling. Namely, latent support vector machines (latent SVMs) and deep learning.

    First, we propose various approaches to group the positive samples into clusters of visually similar instances. Given a fixed representation, the sampled space of the positive distribution is usually structured. The proposed clustering techniques include a novel similarity measure based on exemplar learning, an approach for using additional annotation, and augmenting latent SVM to automatically find clusters whose members can be reliably distinguished from background class. 

    In another effort, a strongly supervised DPM is suggested to study how these models can benefit from privileged information. The extra information comes in the form of semantic parts annotation (i.e. their presence and location). And they are used to constrain DPMs latent variables during or prior to the optimization of the latent SVM. Its effectiveness is demonstrated on the task of animal detection.

    Finally, we generalize the formulation of discriminative latent variable models, including DPMs, to incorporate new set of latent variables representing the structure or properties of negative samples. Thus, we term them as negative latent variables. We show this generalization affects state-of-the-art techniques and helps the visual recognition by explicitly searching for counter evidences of an object presence.

    Following the resurgence of deep networks, in the last works of this thesis we have focused on deep learning in order to produce a generic representation for visual recognition. A Convolutional Network (ConvNet) is trained on a largely annotated image classification dataset called ImageNet with $\sim1.3$ million images. Then, the activations at each layer of the trained ConvNet can be treated as the representation of an input image. We show that such a representation is surprisingly effective for various recognition tasks, making it clearly superior to all the handcrafted features previously used in visual recognition (such as HOG in our first works on DPM). We further investigate the ways that one can improve this representation for a task in mind. We propose various factors involving before or after the training of the representation which can improve the efficacy of the ConvNet representation. These factors are analyzed on 16 datasets from various subfields of visual recognition.

  • 3.
    Azizpour, Hossein
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Arefiyan, Mostafa
    Naderi Parizi, Sobhan
    Carlsson, Stefan
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Spotlight the Negatives: A Generalized Discriminative Latent Model2015Konferensbidrag (Refereegranskat)
    Abstract [en]

    Discriminative latent variable models (LVM) are frequently applied to various visualrecognition tasks. In these systems the latent (hidden) variables provide a formalism formodeling structured variation of visual features. Conventionally, latent variables are de-fined on the variation of the foreground (positive) class. In this work we augment LVMsto includenegativelatent variables corresponding to the background class. We formalizethe scoring function of such a generalized LVM (GLVM). Then we discuss a frameworkfor learning a model based on the GLVM scoring function. We theoretically showcasehow some of the current visual recognition methods can benefit from this generalization.Finally, we experiment on a generalized form of Deformable Part Models with negativelatent variables and show significant improvements on two different detection tasks.

  • 4.
    Azizpour, Hossein
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Carlsson, Stefan
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Self-tuned Visual Subclass Learning with Shared Samples An Incremental Approach2013Artikel, forskningsöversikt (Övrigt vetenskapligt)
    Abstract [en]

    Computer vision tasks are traditionally defined and eval-uated using semantic categories. However, it is known to thefield that semantic classes do not necessarily correspondto a unique visual class (e.g. inside and outside of a car).Furthermore, many of the feasible learning techniques athand cannot model a visual class which appears consistentto the human eye. These problems have motivated the useof 1) Unsupervised or supervised clustering as a prepro-cessing step to identify the visual subclasses to be used ina mixture-of-experts learning regime. 2) Felzenszwalb etal. part model and other works model mixture assignmentwith latent variables which is optimized during learning 3)Highly non-linear classifiers which are inherently capableof modelling multi-modal input space but are inefficient atthe test time. In this work, we promote an incremental viewover the recognition of semantic classes with varied appear-ances. We propose an optimization technique which incre-mentally finds maximal visual subclasses in a regularizedrisk minimization framework. Our proposed approach uni-fies the clustering and classification steps in a single algo-rithm. The importance of this approach is its compliancewith the classification via the fact that it does not need toknow about the number of clusters, the representation andsimilarity measures used in pre-processing clustering meth-ods a priori. Following this approach we show both quali-tatively and quantitatively significant results. We show thatthe visual subclasses demonstrate a long tail distribution.Finally, we show that state of the art object detection meth-ods (e.g. DPM) are unable to use the tails of this distri-bution comprising 50% of the training samples. In fact weshow that DPM performance slightly increases on averageby the removal of this half of the data.

  • 5.
    Azizpour, Hossein
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Laptev, I.
    Object detection using strongly-supervised deformable part models2012Ingår i: Computer Vision – ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part I / [ed] Andrew Fitzgibbon, Svetlana Lazebnik, Pietro Perona, Yoichi Sato, Cordelia Schmid, Springer, 2012, nr PART 1, s. 836-849Konferensbidrag (Refereegranskat)
    Abstract [en]

    Deformable part-based models [1, 2] achieve state-of-the-art performance for object detection, but rely on heuristic initialization during training due to the optimization of non-convex cost function. This paper investigates limitations of such an initialization and extends earlier methods using additional supervision. We explore strong supervision in terms of annotated object parts and use it to (i) improve model initialization, (ii) optimize model structure, and (iii) handle partial occlusions. Our method is able to deal with sub-optimal and incomplete annotations of object parts and is shown to benefit from semi-supervised learning setups where part-level annotation is provided for a fraction of positive examples only. Experimental results are reported for the detection of six animal classes in PASCAL VOC 2007 and 2010 datasets. We demonstrate significant improvements in detection performance compared to the LSVM [1] and the Poselet [3] object detectors.

  • 6.
    Azizpour, Hossein
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Razavian, Ali Sharif
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Maki, Atsuto
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Carlsson, Stefan
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    From Generic to Specific Deep Representations for Visual Recognition2015Ingår i: Proceedings of CVPR 2015, IEEE conference proceedings, 2015Konferensbidrag (Refereegranskat)
    Abstract [en]

    Evidence is mounting that ConvNets are the best representation learning method for recognition. In the common scenario, a ConvNet is trained on a large labeled dataset and the feed-forward units activation, at a certain layer of the network, is used as a generic representation of an input image. Recent studies have shown this form of representation to be astoundingly effective for a wide range of recognition tasks. This paper thoroughly investigates the transferability of such representations w.r.t. several factors. It includes parameters for training the network such as its architecture and parameters of feature extraction. We further show that different visual recognition tasks can be categorically ordered based on their distance from the source task. We then show interesting results indicating a clear correlation between the performance of tasks and their distance from the source task conditioned on proposed factors. Furthermore, by optimizing these factors, we achieve stateof-the-art performances on 16 visual recognition tasks.

  • 7.
    Azizpour, Hossein
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sharif Razavian, Ali
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Maki, Atsuto
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Carlssom, Stefan
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Factors of Transferability for a Generic ConvNet Representation2016Ingår i: IEEE Transaction on Pattern Analysis and Machine Intelligence, ISSN 0162-8828, E-ISSN 1939-3539, Vol. 38, nr 9, s. 1790-1802, artikel-id 7328311Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    Evidence is mounting that Convolutional Networks (ConvNets) are the most effective representation learning method for visual recognition tasks. In the common scenario, a ConvNet is trained on a large labeled dataset (source) and the feed-forward units activation of the trained network, at a certain layer of the network, is used as a generic representation of an input image for a task with relatively smaller training set (target). Recent studies have shown this form of representation transfer to be suitable for a wide range of target visual recognition tasks. This paper introduces and investigates several factors affecting the transferability of such representations. It includes parameters for training of the source ConvNet such as its architecture, distribution of the training data, etc. and also the parameters of feature extraction such as layer of the trained ConvNet, dimensionality reduction, etc. Then, by optimizing these factors, we show that significant improvements can be achieved on various (17) visual recognition tasks. We further show that these visual recognition tasks can be categorically ordered based on their similarity to the source task such that a correlation between the performance of tasks and their similarity to the source task w.r.t. the proposed factors is observed.

  • 8. Carlsson, Stefan
    et al.
    Azizpour, Hossein
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sharif Razavian, Ali
    Sullivan, Josephine
    Smith, Kevin
    The preimage of rectifier network activities2017Konferensbidrag (Refereegranskat)
    Abstract [en]

    We give a procedure for explicitly computing the complete preimage of activities of a layer in a rectifier network with fully connected layers, from knowledge of the weights in the network. The most general characterisation of preimages is as piecewise linear manifolds in the input space with possibly multiple branches. This work therefore complements previous demonstrations of preimages obtained by heuristic optimisation and regularization algorithms Mahendran & Vedaldi (2015; 2016) We are presently empirically evaluating the procedure and it’s ability to extract complete preimages as well as the general structure of preimage manifolds.

  • 9.
    Kazemi, Vahid
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Burenius, Magnus
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Azizpour, Hossein
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Multi-view body part recognition with random forests2013Ingår i: BMVC 2013 - Electronic Proceedings of the British Machine Vision Conference 2013, Bristol, England: British Machine Vision Association , 2013Konferensbidrag (Refereegranskat)
    Abstract [en]

    This paper addresses the problem of human pose estimation, given images taken from multiple dynamic but calibrated cameras. We consider solving this task using a part-based model and focus on the part appearance component of such a model. We use a random forest classifier to capture the variation in appearance of body parts in 2D images. The result of these 2D part detectors are then aggregated across views to produce consistent 3D hypotheses for parts. We solve correspondences across views for mirror symmetric parts by introducing a latent variable. We evaluate our part detectors qualitatively and quantitatively on a dataset gathered from a professional football game.

  • 10. Robertson, Stephanie
    et al.
    Azizpour, Hossein
    KTH, Skolan för datavetenskap och kommunikation (CSC).
    Smith, Kevin
    KTH, Skolan för datavetenskap och kommunikation (CSC).
    Hartman, Johan
    Digital image analysis in breast pathology-from image processing techniques to artificial intelligence2018Ingår i: Translational Research: The Journal of Laboratory and Clinical Medicine, ISSN 1931-5244, E-ISSN 1878-1810, Vol. 194, s. 19-35Artikel, forskningsöversikt (Refereegranskat)
    Abstract [en]

    Breast cancer is the most common malignant disease in women worldwide. In recent decades, earlier diagnosis and better adjuvant therapy have substantially improved patient outcome. Diagnosis by histopathology has proven to be instrumental to guide breast cancer treatment, but new challenges have emerged as our increasing understanding of cancer over the years has revealed its complex nature. As patient demand for personalized breast cancer therapy grows, we face an urgent need for more precise biomarker assessment and more accurate histopathologic breast cancer diagnosis to make better therapy decisions. The digitization of pathology data has opened the door to faster, more reproducible, and more precise diagnoses through computerized image analysis. Software to assist diagnostic breast pathology through image processing techniques have been around for years. But recent breakthroughs in artificial intelligence (AI) promise to fundamentally change the way we detect and treat breast cancer in the near future. Machine learning, a subfield of AI that applies statistical methods to learn from data, has seen an explosion of interest in recent years because of its ability to recognize patterns in data with less need for human instruction. One technique in particular, known as deep learning, has produced groundbreaking results in many important problems including image classification and speech recognition. In this review, we will cover the use of AI and deep learning in diagnostic breast pathology, and other recent developments in digital image analysis.

  • 11.
    Sharif Razavian, Ali
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Azizpour, Hossein
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Maki, Atsuto
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Ek, Carl Henrik
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Carlsson, Stefan
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Persistent Evidence of Local Image Properties in Generic ConvNets2015Ingår i: Image Analysis: 19th Scandinavian Conference, SCIA 2015, Copenhagen, Denmark, June 15-17, 2015. Proceedings / [ed] Paulsen, Rasmus R., Pedersen, Kim S., Springer Publishing Company, 2015, s. 249-262Konferensbidrag (Refereegranskat)
    Abstract [en]

    Supervised training of a convolutional network for object classification should make explicit any information related to the class of objects and disregard any auxiliary information associated with the capture of the image or thevariation within the object class. Does this happen in practice? Although this seems to pertain to the very final layers in the network, if we look at earlier layers we find that this is not the case. Surprisingly, strong spatial information is implicit. This paper addresses this, in particular, exploiting the image representation at the first fully connected layer,i.e. the global image descriptor which has been recently shown to be most effective in a range of visual recognition tasks. We empirically demonstrate evidences for the finding in the contexts of four different tasks: 2d landmark detection, 2d object keypoints prediction, estimation of the RGB values of input image, and recovery of semantic label of each pixel. We base our investigation on a simple framework with ridge rigression commonly across these tasks,and show results which all support our insight. Such spatial information can be used for computing correspondence of landmarks to a good accuracy, but should potentially be useful for improving the training of the convolutional nets for classification purposes.

  • 12.
    Sharif Razavian, Ali
    et al.
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Azizpour, Hossein
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Sullivan, Josephine
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    Carlsson, Stefan
    KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
    CNN features off-the-shelf: An Astounding Baseline for Recognition2014Ingår i: Proceedings of CVPR 2014, 2014Konferensbidrag (Refereegranskat)
    Abstract [en]

    Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the OverFeat network which was trained to perform object classification on ILSVRC13. We use features extracted from the OverFeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets. We selected these tasks and datasets as they gradually move further away from the original task and data the OverFeat network was trained to solve. Astonishingly, we report consistent superior results compared to the highly tuned state-of-the-art systems in all the visual classification tasks on various datasets. For instance retrieval it consistently outperforms low memory footprint methods except for sculptures dataset. The results are achieved using a linear SVM classifier (or L2 distance in case of retrieval) applied to a feature representation of size 4096 extracted from a layer in the net. The representations are further modified using simple augmentation techniques e.g. jittering. The results strongly suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.

  • 13.
    Smith, Kevin
    et al.
    KTH, Centra, Science for Life Laboratory, SciLifeLab. KTH, Skolan för elektroteknik och datavetenskap (EECS), Beräkningsvetenskap och beräkningsteknik (CST).
    Piccinini, Filippo
    IRCCS, Ist Sci Romagnolo Studio & Cura Tumori IRST, Via P Maroncelli 40, I-47014 Meldola, FC, Italy..
    Balassa, Tamas
    Hungarian Acad Sci, Synthet & Syst Biol Unit, BRC, Temesvari Krt 62, H-6726 Szeged, Hungary..
    Koos, Krisztian
    Hungarian Acad Sci, Synthet & Syst Biol Unit, BRC, Temesvari Krt 62, H-6726 Szeged, Hungary..
    Danka, Tivadar
    Hungarian Acad Sci, Synthet & Syst Biol Unit, BRC, Temesvari Krt 62, H-6726 Szeged, Hungary..
    Azizpour, Hossein
    KTH, Skolan för elektroteknik och datavetenskap (EECS). KTH, Centra, Science for Life Laboratory, SciLifeLab.
    Horvath, Peter
    Hungarian Acad Sci, Synthet & Syst Biol Unit, BRC, Temesvari Krt 62, H-6726 Szeged, Hungary.;Univ Helsinki, Inst Mol Med Finland, Tukholmankatu 8, FIN-00014 Helsinki, Finland..
    Phenotypic Image Analysis Software Tools for Exploring and Understanding Big Image Data from Cell-Based Assays2018Ingår i: CELL SYSTEMS, ISSN 2405-4712, Vol. 6, nr 6, s. 636-653Artikel, forskningsöversikt (Refereegranskat)
    Abstract [en]

    Phenotypic image analysis is the task of recognizing variations in cell properties using microscopic image data. These variations, produced through a complex web of interactions between genes and the environment, may hold the key to uncover important biological phenomena or to understand the response to a drug candidate. Today, phenotypic analysis is rarely performed completely by hand. The abundance of high-dimensional image data produced by modern high-throughput microscopes necessitates computational solutions. Over the past decade, a number of software tools have been developed to address this need. They use statistical learning methods to infer relationships between a cell's phenotype and data from the image. In this review, we examine the strengths and weaknesses of non-commercial phenotypic image analysis software, cover recent developments in the field, identify challenges, and give a perspective on future possibilities.

  • 14.
    Srinivasan, P. A.
    et al.
    KTH, Skolan för teknikvetenskap (SCI), Mekanik. KTH, Skolan för teknikvetenskap (SCI), Centra, Linné Flow Center, FLOW. KTH, Skolan för elektroteknik och datavetenskap (EECS). KTH, Centra, SeRC - Swedish e-Science Research Centre.
    Guastoni, L.
    KTH, Centra, SeRC - Swedish e-Science Research Centre. KTH Mech, Linne FLOW Ctr, SE-10044 Stockholm, Sweden.;Swedish E Sci Res Ctr SeRC, SE-10044 Stockholm, Sweden..
    Azizpour, Hossein
    KTH, Centra, SeRC - Swedish e-Science Research Centre. KTH, Skolan för elektroteknik och datavetenskap (EECS).
    Schlatter, Philipp
    KTH, Centra, SeRC - Swedish e-Science Research Centre. KTH, Skolan för teknikvetenskap (SCI), Mekanik. KTH, Skolan för teknikvetenskap (SCI), Centra, Linné Flow Center, FLOW.
    Vinuesa, Ricardo
    KTH, Centra, SeRC - Swedish e-Science Research Centre. KTH, Skolan för teknikvetenskap (SCI), Mekanik. KTH, Skolan för teknikvetenskap (SCI), Centra, Linné Flow Center, FLOW.
    Predictions of turbulent shear flows using deep neural networks2019Ingår i: Physical Review Fluids, E-ISSN 2469-990X, Vol. 4, nr 5, artikel-id 054603Artikel i tidskrift (Refereegranskat)
    Abstract [en]

    In the present work, we assess the capabilities of neural networks to predict temporally evolving turbulent flows. In particular, we use the nine-equation shear flow model by Moehlis et al. [New J. Phys. 6, 56 (2004)] to generate training data for two types of neural networks: the multilayer perceptron (MLP) and the long short-term memory (LSTM) networks. We tested a number of neural network architectures by varying the number of layers, number of units per layer, dimension of the input, and weight initialization and activation functions in order to obtain the best configurations for flow prediction. Because of its ability to exploit the sequential nature of the data, the LSTM network outperformed the MLP. The LSTM led to excellent predictions of turbulence statistics (with relative errors of 0.45% and 2.49% in mean and fluctuating quantities, respectively) and of the dynamical behavior of the system (characterized by Poincare maps and Lyapunov exponents). This is an exploratory study where we consider a low-order representation of near-wall turbulence. Based on the present results, the proposed machine-learning framework may underpin future applications aimed at developing accurate and efficient data-driven subgrid-scale models for large-eddy simulations of more complex wall-bounded turbulent flows, including channels and developing boundary layers.

  • 15.
    Teye, Mattias
    et al.
    KTH, Skolan för elektroteknik och datavetenskap (EECS).
    Azizpour, Hossein
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Robotik, perception och lärande, RPL.
    Smith, Kevin
    KTH, Skolan för elektroteknik och datavetenskap (EECS), Beräkningsvetenskap och beräkningsteknik (CST). Science for Life Laboratory.
    Bayesian Uncertainty Estimation for Batch Normalized Deep Networks2018Konferensbidrag (Refereegranskat)
    Abstract [en]

    We show that training a deep network using batch normalization is equivalent to approximate inference in Bayesian models. We further demonstrate that this finding allows us to make meaningful estimates of the model uncertainty using conventional architectures, without modifications to the network or the training procedure. Our approach is thoroughly validated by measuring the quality of uncertainty in a series of empirical experiments on different tasks. It outperforms baselines with strong statistical significance, and displays competitive performance with recent Bayesian approaches

1 - 15 av 15
RefereraExporteraLänk till träfflistan
Permanent länk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf