• Home
  • Search
  • A Training Method Using DNN-guided Layerwise Pretraining for Deep Gaussian Processes
  • Cite Icon5
  • https://doi.org/10.1109/icassp.2019.8683372Copy DOI Icon

A Training Method Using DNN-guided Layerwise Pretraining for Deep Gaussian Processes

  • May 1, 2019
  • Tomoki Koriyama +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper proposes a novel framework of training method of deep Gaussian processes (DGPs). DGPs are deep architecture models based on stacked multiple GPs, which can overcome the limitation of single-layer GPs. Although a stochastic variational inference (SVI)- based method has been proposed for DGP training with an arbitrary amount of training data, it does not always update model parameters appropriately due to repeated Monte Carlo sampling of multiple GPs. To resolve this problem, we propose a pretraining method to determine initial parameters of DGPs. In the proposed method, layer-wise training of single-layer GPs is performed using the hidden-layer values obtained by a deep neural network (DNN) that has an analogous structure to a target DGP model. The proposed method utilizes the characteristics of single-layer GPs and deep neural network (DNN) whose training is easier than DGP's. Experimental results using two speech synthesis databases with approximately 600 K and 1.4 M training data points, respectively, which were composed of hundreds of input and output features, gave the effectiveness of the proposed method.

Similar Papers
  • Conference Article
  • Citations1

Automatically Designed Deep Gaussian Process for Turbomachinery Application

  • Jun 07, 2021
  • Yuan Jin +2
  • Conference Article
  • Citations3

Multi-Speaker Text-to-Speech Synthesis Using Deep Gaussian Processes

  • Oct 25, 2020
  • Kentaro Mitsui +2
  • Research Article
  • Citations7

Deep Gaussian process based multi-speaker speech synthesis with latent speaker representation

  • Jul 10, 2021
  • Speech Communication
  • Kentaro Mitsui +2
  • Book Chapter

Multi-view Deep Gaussian Process with a Pre-training Acceleration Technique

  • Jan 01, 2020
  • Advances in Knowledge Discovery and Data Mining
  • Han Zhu +2
  • Research Article
  • Citations32

Empirical Assessment of Deep Gaussian Process Surrogate Models for Engineering Problems

  • Sep 18, 2020
  • Journal of Aircraft
  • Dushhyanth Rajaram +6
  • Conference Article
  • Citations7

Fast and Efficient DNN Deployment via Deep Gaussian Transfer Learning

  • Oct 01, 2021
  • Qi Sun +6
  • Book Chapter
  • Citations5

Deep Gaussian Processes Using Expectation Propagation and Monte Carlo Methods

  • Jan 01, 2021
  • Gonzalo Hernández-Muñoz +2
  • Research Article
  • Citations1

Alpha-divergence minimization for deep Gaussian processes

  • Aug 22, 2022
  • International Journal of Approximate Reasoning
  • Carlos Villacampa-Calvo +2
  • Research Article
  • Citations27

Deep Gaussian Process Emulation using Stochastic Imputation

  • Oct 11, 2022
  • Technometrics
  • Deyu Ming +2
  • Research Article

Abstract 2316: A deep Gaussian process (DGP)-based prediction model for immunecheckpoint inhibitor (ICI) response in gastric cancer (GC)

  • Mar 22, 2024
  • Cancer Research
  • Sunho Park +3
  • Research Article
  • Citations94

Active Learning for Deep Gaussian Process Surrogates

  • Jan 25, 2022
  • Technometrics
  • Annie Sauer +2
  • PDF
  • Research Article
  • Citations3

Deep Gaussian Process for the Approximation of a Quadratic Eigenvalue Problem: Application to Friction-Induced Vibration

  • Jun 10, 2022
  • Vibration
  • Jeremy Sadet +4
  • Research Article
  • Citations3

Detecting Causality using Deep Gaussian Processes.

  • Nov 01, 2019
  • Conference record. Asilomar Conference on Signals, Systems & Computers
  • Guanchao Feng +2
  • Preprint Article

Feasibility of Multiple Advanced Machine Learning Techniques for Synthetic Finite-fault Earthquake Ground Motion Data

  • Mar 16, 2023
  • Manuel Titos Luzon +2
  • Research Article
  • Citations5

Neural Operator Variational Inference Based on Regularized Stein Discrepancy for Deep Gaussian Processes.

  • Apr 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Jian Xu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.