Change search
Refine search result
1 - 11 of 11
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1. Qu, An
    et al.
    Zhang, Cheng
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Ackermann, Paul
    Kjellström, Hedvig
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Bridging Medical Data Inference to Achilles Tendon Rupture Rehabilitation2016Conference paper (Refereed)
  • 2.
    Zhang, Cheng
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Structured Representation Using Latent Variable Models2016Doctoral thesis, monograph (Other academic)
    Abstract [en]

    Over the past two centuries the industrial revolution automated a great part of work that involved human muscles. Recently, since the beginning of the 21st century, the focus has shifted towards automating work that is involving our brain to further improve our lives. This is accomplished by establishing human-level intelligence through machines, which lead to the growth of the field of artificial intelligence. Machine learning is a core component of artificial intelligence. While artificial intelligence focuses on constructing an entire intelligence system, machine learning focuses on the learning ability and the ability to further use the learned knowledge for different tasks. This thesis targets the field of machine learning, especially structured representation learning, which is key for various machine learning approaches.

    Humans sense the environment, extract information and make action decisions based on abstracted information. Similarly, machines receive data, abstract information from data through models and make decisions about the unknown through inference. Thus, models provide a mechanism for machines to abstract information. This commonly involves learning useful representations which are desirably compact, interpretable and useful for different tasks. In this thesis, the contribution relates to the design of efficient representation models with latent variables. To make the models useful, efficient inference algorithms are derived to fit the models to data. We apply our models to various applications from different domains, namely E-health, robotics, text mining, computer vision and recommendation systems.

    The main contribution of this thesis relates to advancing latent variable models and deriving associated inference schemes for representation learning. This is pursued in three different directions. Firstly, through supervised models, where better representations can be learned knowing the tasks, corresponding to situated knowledge of humans. Secondly, through structured representation models, with which different structures, such as factorized ones, are used for latent variable models to form more efficient representations. Finally, through non-parametric models, where the representation is determined completely by the data. Specifically, we propose several new models combining supervised learning and factorized representation as well as a further model combining non-parametric modeling and supervised approaches. Evaluations show that these new models provide generally more efficient representations and a higher degree of interpretability.

    Moreover, this thesis contributes by applying these proposed models in different practical scenarios, demonstrating that these models can provide efficient latent representations. Experimental results show that our models improve the performance for classical tasks, such as image classification and annotations, robotic scene and action understanding. Most notably, one of our models is applied to a novel problem in E-health, namely diagnostic prediction using discomfort drawings. Experimental investigation show here that our model can achieve significant results in automatic diagnosing and provides profound understanding of typical symptoms. This motivates novel decision support systems for healthcare personnel.

  • 3.
    Zhang, Cheng
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Ek, Carl Henrik
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Damianou, Andreas
    The University of Sheffield.
    Kjellström, Hedvig
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Factorized Topic Models2013Conference paper (Refereed)
    Abstract [en]

    In this paper we present a modification to a latent topic model, which makes themodel exploit supervision to produce a factorized representation of the observeddata. The structured parameterization separately encodes variance that is sharedbetween classes from variance that is private to each class by the introduction of anew prior over the topic space. The approach allows for a more efficient inferenceand provides an intuitive interpretation of the data in terms of an informative signaltogether with structured noise. The factorized representation is shown to enhanceinference performance for image, text, and video classification.

  • 4.
    Zhang, Cheng
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
    Ek, Carl Henrik
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
    Gratal, Xavi
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
    Pokorny, Florian T.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
    Kjellström, Hedvig
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
    Supervised Hierarchical Dirichlet Processes with Variational Inference2013In: 2013 IEEE International Conference on Computer Vision Workshops (ICCVW), IEEE , 2013, p. 254-261Conference paper (Refereed)
    Abstract [en]

    We present an extension to the Hierarchical Dirichlet Process (HDP), which allows for the inclusion of supervision. Our model marries the non-parametric benefits of HDP with those of Supervised Latent Dirichlet Allocation (SLDA) to enable learning the topic space directly from data while simultaneously including the labels within the model. The proposed model is learned using variational inference which allows for the efficient use of a large training dataset. We also present the online version of variational inference, which makes the method scalable to very large datasets. We show results comparing our model to a traditional supervised parametric topic model, SLDA, and show that it outperforms SLDA on a number of benchmark datasets.

  • 5.
    Zhang, Cheng
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Gartrell, Mike
    Microsoft R&D.
    Minka, Thomas. P.
    Microsoft Research .
    Zaykov, Yordan
    Microsoft Research .
    Guiver, John
    Microsoft Research .
    GroupBox: A generative model for group recommendation2015Report (Refereed)
    Abstract [en]

    In this paper, we present a principled probabilistic framework – GroupBox – for making recommendations to groups. GroupBox is able to model user influence within a group, the suitability of an item to a group context, and the differences in user preference between individual and group contexts. Efficient scalable inference algorithms are used for GroupBox, which makes it applicable to large-scale datasets. We run experiments on a large-scale TV viewing dataset collected by Nielsen and show how the model can be used to understand both context and influence. The experimental results on the large scale real data provide a deep understanding of the individual behaviours in group context.

  • 6. Zhang, Cheng
    et al.
    Hua, Qiang
    Applications of Genome-Scale Metabolic Models in Biotechnology and Systems Medicine: Application of GEMs2016In: Frontiers in Physiology, ISSN 1664-042X, E-ISSN 1664-042X, Vol. 6, no January, article id 413Article in journal (Refereed)
    Abstract [en]

    Genome-scale metabolic models (GEMs) have become a popular tool for systems biology, and they have been used in many fields such as industrial biotechnology and systems medicine. Since more and more studies are being conducted using GEMs, they have recently received considerable attention. In this review, we introduce the basic concept of GEMs and provide an overview of their applications in biotechnology, systems medicine, and some other fields. In addition, we describe the general principle of the applications and analyses built on GEMs. The purpose of this review is to introduce the application of GEMs in biological analysis and to promote its wider use by biologists.

  • 7.
    Zhang, Cheng
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Kjellström, Hedvig
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    How to Supervise Topic Models2014In: Computer Vision - ECCV 2014 Workshops: Zurich, Switzerland, September 6-7 and 12, 2014, Proceedings, Part II / [ed] Agapito, Bronstein, Rother, Zurich: Springer Publishing Company, 2014, p. 500-515Chapter in book (Refereed)
    Abstract [en]

    Supervised topic models are important machine learning tools whichhave been widely used in computer vision as well as in other domains. However,there is a gap in the understanding of the supervision impact on the model. Inthis paper, we present a thorough analysis on the behaviour of supervised topicmodels using Supervised Latent Dirichlet Allocation (SLDA) and propose twofactorized supervised topic models, which factorize the topics into signal andnoise. Experimental results on both synthetic data and real-world data for computer vision tasks show that supervision need to be boosted to be effective andfactorized topic models are able to enhance the performance.

  • 8.
    Zhang, Cheng
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Kjellström, Hedvig
    KTH, School of Computer Science and Communication (CSC), Robotics, perception and learning, RPL.
    Bertilson, Bo C.
    Diagnostic Prediction Using Discomfort Drawings2016Conference paper (Refereed)
  • 9.
    Zhang, Cheng
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Kjellström, Hedvig
    KTH, School of Computer Science and Communication (CSC), Robotics, perception and learning, RPL.
    Ek, Carl Henrik
    Bertilson, Bo C.
    Diagnostic Prediction Using Discomfort Drawing with IBTM2016Conference paper (Refereed)
    Abstract [en]

    In this paper, we explore the possibility to apply machine learning to make diagnostic predictions using discomfort drawings. A discomfort drawing is an intuitive way for patients to express discomfort and pain related symptoms. These drawings have proven to be an effective method to collect patient data and make diagnostic decisions in real-life practice. A dataset from real-world patient cases is collected for which medical experts provide diagnostic labels. Next, we use a factorized multimodal topic model, Inter-Battery Topic Model (IBTM), to train a system that can make diagnostic predictions given an unseen discomfort drawing. The number of output diagnostic labels is determined by using mean-shift clustering on the discomfort drawing. Experimental results show reasonable predictions of diagnostic labels given an unseen discomfort drawing. Additionally, we generate synthetic discomfort drawings with IBTM given a diagnostic label, which results in typical cases of symptoms. The positive result indicates a significant potential of machine learning to be used for parts of the pain diagnostic process and to be a decision support system for physicians and other health care personnel.

  • 10.
    Zhang, Cheng
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP.
    Mandt, Stephan
    Kjellström, Hedvig
    KTH, School of Computer Science and Communication (CSC), Robotics, perception and learning, RPL.
    Balanced Population Stochastic Variational Inference2016Conference paper (Refereed)
  • 11.
    Zhang, Cheng
    et al.
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
    Song, Dan
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
    Kjellström, Hedvig
    KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
    Contextual Modeling with Labeled Multi-LDA2013In: 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE , 2013, p. 2264-2271Conference paper (Refereed)
    Abstract [en]

    Learning about activities and object affordances from human demonstration are important cognitive capabilities for robots functioning in human environments, for example, being able to classify objects and knowing how to grasp them for different tasks. To achieve such capabilities, we propose a Labeled Multi-modal Latent Dirichlet Allocation (LM-LDA), which is a generative classifier trained with two different data cues, for instance, one cue can be traditional visual observation and another cue can be contextual information. The novel aspects of the LM-LDA classifier, compared to other methods for encoding contextual information are that, I) even with only one of the cues present at execution time, the classification will be better than single cue classification since cue correlations are encoded in the model, II) one of the cues (e.g., common grasps for the observed object class) can be inferred from the other cue (e.g., the appearance of the observed object). This makes the method suitable for robot online and transfer learning; a capability highly desirable in cognitive robotic applications. Our experiments show a clear improvement for classification and a reasonable inference of the missing data.

1 - 11 of 11
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf