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

[1] Calibrating Deep Convolutional Gaussian Processes
Tran, G-L
Bonilla, E., V
Cunningham, J. P.
Michiardi, P.
Filippone, M.
22ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 89, 2019, 89
[2] Convolutional Normalizing Flows for Deep Gaussian Processes
Yu, Haibin
Liu, Dapeng
Low, Bryan Kian Hsiang
Jaillet, Patrick
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
[3] Bayesian Image Classification with Deep Convolutional Gaussian Processes
Dutordoir, Vincent
van der Wilk, Mark
Artemev, Artem
Hensman, James
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 1529 - 1538
[4] DEEP CONVOLUTIONAL GAUSSIAN PROCESSES FOR MMWAVE OUTDOOR LOCALIZATION
Wang, Xuyu
Patil, Mohini
Yang, Chao
Mao, Shiwen
Patel, Palak Anilkumar
2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 8323 - 8327
[5] Decision Making under Uncertainty with Convolutional Deep Gaussian Processes
Jain, Dinesh
Anumasa, Srinivas
Srijith, P. K.
PROCEEDINGS OF THE 7TH ACM IKDD CODS AND 25TH COMAD (CODS-COMAD 2020), 2020, : 143 - 151
[6] Bayesian Link Prediction with Deep Graph Convolutional Gaussian Processes
Opolka, Felix L.
Lio, Pietro
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
[7] Convolutional Gaussian Processes
van der Wilk, Mark
Rasmussen, Carl Edward
Liensman, James
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[8] Graph Convolutional Gaussian Processes
Walker, Ian
Glocker, Ben
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
[9] How deep are deep Gaussian processes?
Dunlop, Matthew M.
Girolami, Mark A.
Stuart, Andrew M.
Teckentrup, Aretha L.
Journal of Machine Learning Research, 2018, 19 : 1 - 46
[10] How Deep Are Deep Gaussian Processes?
Dunlop, Matthew M.
Girolami, Mark A.
Stuart, Andrew M.
Teckentrup, Aretha L.
JOURNAL OF MACHINE LEARNING RESEARCH, 2018, 19

← 1 2 3 4 5 →