Deep Generalized Convolutional Sum-Product Networks

被引:0
|
作者
van de Wolfshaar, Jos [1 ,2 ]
Pronobis, Andrzej [1 ,3 ]
机构
[1] KTH Royal Inst Technol, Stockholm, Sweden
[2] MessageBird, Amsterdam, Netherlands
[3] Univ Washington, Seattle, WA 98195 USA
基金
瑞典研究理事会;
关键词
Sum-Product Networks; Deep Probabilistic Models; Image Representations;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sum-Product Networks (SPNs) are hierarchical, graphical models that combine benefits of deep learning and probabilistic modeling. SPNs offer unique advantages to applications demanding exact probabilistic inference over high-dimensional, noisy inputs. Yet, compared to convolutional neural nets, they struggle with capturing complex spatial relationships in image data. To alleviate this issue, we introduce Deep Generalized Convolutional Sum-Product Networks (DGC-SPNs), which encode spatial features in a way similar to CNNs, while preserving the validity of the probabilistic SPN model. As opposed to existing SPN-based image representations, DGC-SPNs allow for overlapping convolution patches through a novel parameterization of dilations and strides, resulting in significantly improved feature coverage and feature resolution. DGC-SPNs substantially outperform other SPN architectures across several visual datasets and for both generative and discriminative tasks, including image inpainting and classification. These contributions are reinforced by the first simple, scalable, and GPU-optimized implementation of SPNs, integrated with the widely used Keras/TensorFlow framework. The resulting model is fully probabilistic and versatile, yet efficient and straightforward to apply in practical applications in place of traditional deep nets.
引用
下载
收藏
页码:533 / 544
页数:12
相关论文
共 50 条
  • [31] Certified Data Removal in Sum-Product Networks
    Becker, Alexander
    Liebig, Thomas
    2022 IEEE INTERNATIONAL CONFERENCE ON KNOWLEDGE GRAPH (ICKG), 2022, : 14 - 21
  • [32] Maximum A Posteriori Inference in Sum-Product Networks
    Mei, Jun
    Jiang, Yong
    Tu, Kewei
    THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 1923 - 1930
  • [33] Towards Scalable and Robust Sum-Product Networks
    Correia, Alvaro H. C.
    de Campos, Cassio P.
    SCALABLE UNCERTAINTY MANAGEMENT, SUM 2019, 2019, 11940 : 409 - 422
  • [34] On the Sample Complexity of Learning Sum-Product Networks
    Aden-Ali, Ishaq
    Ashtiani, Hassan
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 4508 - 4518
  • [35] Greedy Structure Search for Sum-Product Networks
    Dennis, Aaron
    Ventura, Dan
    PROCEEDINGS OF THE TWENTY-FOURTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI), 2015, : 932 - 938
  • [36] Sum-Product decoding of convolutional code for wireless LAN standard
    Shohon, Toshiyuki
    Razi, Fakhrur
    Ogawa, Yuuichi
    Ogiwara, Haruo
    IWSDA'09: PROCEEDINGS OF THE FOURTH INTERNATIONAL WORKSHOP ON SIGNAL DESIGN AND ITS APPLICATIONS IN COMMUNICATIONS, 2009, : 68 - +
  • [37] Product graphs, sum-product graphs and sum-product estimates over finite rings
    Le Anh Vinh
    FORUM MATHEMATICUM, 2015, 27 (03) : 1639 - 1655
  • [38] Acoustic-articulatory relationships and inversion in sum-product and deep-belief networks
    Rudzicz, Frank
    Frydenlund, Arvid
    Robertson, Sean
    Thaine, Patricia
    SPEECH COMMUNICATION, 2016, 79 : 61 - 73
  • [39] Online Structure-Search for Sum-Product Networks
    Dennis, Aaron
    Ventura, Dan
    2017 16TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2017, : 155 - 160
  • [40] A Unified Approach for Learning the Parameters of Sum-Product Networks
    Zhao, Han
    Poupart, Pascal
    Gordon, Geoff
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 29 (NIPS 2016), 2016, 29