Deep Convolutional Gaussian Processes

被引：15

作者：

Blomqvist, Kenneth ^{[1
,2
]}

Kaski, Samuel ^{[1
,2
]}

Heinonen, Markus ^{[1
,2
]}

机构：

[1] Aalto Univ, Espoo, Finland

[2] Helsinki Inst Informat Technol HIIT, Espoo, Finland

来源：

MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2019, PT II | 2020年 / 11907卷

关键词：

Gaussian processes; Convolutions; Variational inference;

D O I：

10.1007/978-3-030-46147-8_35

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure. The model is a principled Bayesian framework for detecting hierarchical combinations of local features for image classification. We demonstrate greatly improved image classification performance compared to current convolutional Gaussian process approaches on the MNIST and CIFAR-10 datasets. In particular, we improve state-of-the-art CIFAR-10 accuracy by over 10% points.

引用

页码：582 / 597

页数：16

共 50 条

[41] Learning with deep Gaussian processes and homothety in weather simulation
Lassana Coulibaly
Cheick Abdoul Kadir A. Kounta
Bernard Kamsu-Foguem
Fana Tangara
Neural Computing and Applications, 2022, 34 : 17441 - 17453
[42] Doubly Stochastic Variational Inference for Deep Gaussian Processes
Salimbeni, Hugh
Deisenroth, Marc Peter
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[43] Approximate Inference Turns Deep Networks into Gaussian Processes
Khan, Mohammad Emtiyaz
Immer, Alexander
Abedi, Ehsan
Korzepa, Maciej
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
[44] Wide Neural Networks with Bottlenecks are Deep Gaussian Processes
Agrawal, Devanshu
Papamarkou, Theodore
Hinkle, Jacob
JOURNAL OF MACHINE LEARNING RESEARCH, 2020, 21
[45] Learning with deep Gaussian processes and homothety in weather simulation
Coulibaly, Lassana
Kounta, Cheick Abdoul Kadir A.
Kamsu-Foguem, Bernard
Tangara, Fana
NEURAL COMPUTING & APPLICATIONS, 2022, 34 (20): : 17441 - 17453
[46] Alpha-divergence minimization for deep Gaussian processes
Villacampa-Calvo, Carlos
Hernandez-Munoz, Gonzalo
Hernandez-Lobato, Daniel
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2022, 150 : 139 - 171
[47] Likelihood-free inference with deep Gaussian processes
Aushev, Alexander
Pesonen, Henri
Heinonen, Markus
Corander, Jukka
Kaski, Samuel
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2022, 174
[48] Probabilistic Deep Ordinal Regression Based on Gaussian Processes
Liu, Yanzhu
Wang, Fan
Kong, Adams Wai Kin
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 5300 - 5308
[49] Identification of Atmospheric Variable Using Deep Gaussian Processes
Jancic, Mitja
Kocijan, Jus
Grasic, Bostjan
IFAC PAPERSONLINE, 2018, 51 (05): : 43 - 48
[50] Implicit Posterior Variational Inference for Deep Gaussian Processes
Yu, Haibin
Chen, Yizhou
Dai, Zhongxiang
Low, Bryan Kian Hsiang
Jaillet, Patrick
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32

← 1 2 3 4 5 →