Processing of ferroelectric ceramics and thin films through the microstructure con...
Evidence of Students' Critical Thinking Development in Chemistry Classes
New theoretical and empirical developments in political economy
| Full text | |
| Author(s): |
de Souza, Daniel Augusto
;
Nikitin, Alexander
;
John, S. T.
;
Ross, Magnus
;
Alvarez, Mauricio A.
;
Deisenroth, Marc Peter
;
Gomes, Joao P. P.
;
Mesquita, Diego
;
Mattos, Cesar Lincoln C.
Total Authors: 9
|
| Document type: | Journal article |
| Source: | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017); v. N/A, p. 11-pg., 2023-01-01. |
| Abstract | |
Gaussian processes (GPs) can provide a principled approach to uncertainty quantification with easy-to-interpret kernel hyperparameters, such as the lengthscale, which controls the correlation distance of function values. However, selecting an appropriate kernel can be challenging. Deep GPs avoid manual kernel engineering by successively parameterizing kernels with GP layers, allowing them to learn low-dimensional embeddings of the inputs that explain the output data. Following the architecture of deep neural networks, the most common deep GPs warp the input space layer-by-layer but lose all the interpretability of shallow GPs. An alternative construction is to successively parameterize the lengthscale of a kernel, improving the interpretability but ultimately giving away the notion of learning lower-dimensional embeddings. Unfortunately, both methods are susceptible to particular pathologies which may hinder fitting and limit their interpretability. This work proposes a novel synthesis of both previous approaches: Thin and Deep GP (TDGP). Each TDGP layer defines locally linear transformations of the original input data maintaining the concept of latent embeddings while also retaining the interpretation of lengthscales of a kernel. Moreover, unlike the prior methods, TDGP induces non-pathological manifolds that admit learning lower-dimensional representations. We show with theoretical and experimental results that i) TDGP is, unlike previous models, tailored to specifically discover lower-dimensional manifolds in the input data, ii) TDGP behaves well when increasing the number of layers, and iii) TDGP performs well in standard benchmark datasets. (AU) | |
| FAPESP's process: | 23/00815-6 - Reimagining AI for a world on fire |
| Grantee: | Diego Parente Paiva Mesquita |
| Support Opportunities: | Regular Research Grants |