Deep kernel learning

AG Wilson, Z Hu, R Salakhutdinov… - Artificial intelligence …, 2016 - proceedings.mlr.press
… In Figure 4 we show the spectral density (the Fourier transform) of the base kernels learned
through our deep kernel learning method. The expressive spectral mixture (SM) kernel

The promises and pitfalls of deep kernel learning

SW Ober, CE Rasmussen… - Uncertainty in Artificial …, 2021 - proceedings.mlr.press
Deep kernel learning and related techniques promise to … the overfitting from overparameterized
deep kernel learning, in … fully Bayesian treatment of deep kernel learning can rectify this …

Stochastic variational deep kernel learning

AG Wilson, Z Hu… - Advances in neural …, 2016 - proceedings.neurips.cc
kernel methods with the inductive biases of deep learning architectures. We propose a novel
deep kernel learningdeep kernel learning approaches to enable classification, multi-task …

Adaptive deep kernel learning

P Tossou, B Dura, F Laviolette, M Marchand… - arXiv preprint arXiv …, 2019 - arxiv.org
learning in the deep kernel learning framework where test-time adaptation is achieved through
kernel … We also create another layer of adaptation by allowing task-specific kernels that …

Bridging deep and multiple kernel learning: A review

T Wang, L Zhang, W Hu - Information Fusion, 2021 - Elsevier
… of deep kernel methods (or deep kernel learning), we choose to focus on the deep MKL …
shown great success in automated kernel learning and optimization for kernel methods. The rest …

Nonlinear deep kernel learning for image annotation

M Jiu, H Sahbi - IEEE Transactions on Image Processing, 2017 - ieeexplore.ieee.org
… A supervised learning of convolutional kernel … ], our deep kernel networks, proposed in this
paper, learn implicit mapping functions using nonlinear combinations of elementary kernels. …

To understand deep learning we need to understand kernel learning

M Belkin, S Ma, S Mandal - … on Machine Learning, 2018 - proceedings.mlr.press
Deep models, which are typically heavily over-parametrized, tend to fit the training … deep
learning. Using six realworld and two synthetic datasets, we establish experimentally that kernel

Kernel methods for deep learning

Y Cho, L Saul - Advances in neural information processing …, 2009 - proceedings.neurips.cc
… how to use kernel methods in deep architectures [7]. We show how to train deep kernel-based …
Using the arc-cosine kernels in the previous section, these multilayer kernel machines (…

[PDF][PDF] Overview of Deep Kernel Learning Based Techniques and Applications.

X Chen, X Peng, JB Li, Y Peng - J. Netw. Intell., 2016 - bit.kuas.edu.tw
deep kernel learning can be constructed in section 3. Section 4 exhibits the combination of
kernel methods and deep … paper and gives the outlook of future work in deep kernel learning. …

[PDF][PDF] Deep Spectral Kernel Learning.

H Xue, ZF Wu, WX Sun - IJCAI, 2019 - ijcai.org
deep kernel algorithms have been presented to try to link kernel method with deep learning.
… A representer theorem for deep kernel learning. arXiv preprint arXiv:1709.10441, 2017. […