Search Results for author:
Found 10 papers, 5 papers with code
Improving the Expressive Power of Deep Neural Networks through Integral Activation Transform
The impressive expressive power of deep neural networks (DNNs) underlies their widespread applicability.
Diffusion-Model-Assisted Supervised Learning of Generative Models for Density Estimation
Unlike existing diffusion models that train neural networks to learn the score function, we develop a training-free score estimation method.
An Ensemble Score Filter for Tracking High-Dimensional Nonlinear Dynamical Systems
A major drawback of existing filtering methods, e. g., particle filters or ensemble Kalman filters, is the low accuracy in handling high-dimensional and highly nonlinear problems.
TransNet: Transferable Neural Networks for Partial Differential Equations
Transfer learning for partial differential equations (PDEs) is to develop a pre-trained neural network that can be used to solve a wide class of PDEs.
Convergence Analysis for Training Stochastic Neural Networks via Stochastic Gradient Descent
In this paper, we carry out numerical analysis to prove convergence of a novel sample-wise back-propagation method for training a class of stochastic neural networks (SNNs).
A Kernel Learning Method for Backward SDE Filter
In this paper, we develop a kernel learning backward SDE filter method to estimate the state of a stochastic dynamical system based on its partial noisy observations.
Disentangled Variational Information Bottleneck for Multiview Representation Learning
Multiview data contain information from multiple modalities and have potentials to provide more comprehensive features for diverse machine learning tasks.
A Backward SDE Method for Uncertainty Quantification in Deep Learning
We develop a probabilistic machine learning method, which formulates a class of stochastic neural networks by a stochastic optimal control problem.
A Two-Stage Approach to Device-Robust Acoustic Scene Classification
To improve device robustness, a highly desirable key feature of a competitive data-driven acoustic scene classification (ASC) system, a novel two-stage system based on fully convolutional neural networks (CNNs) is proposed.
Ranked #1 on
Acoustic Scene Classification
on TAU Urban Acoustic Scenes 2019
(using extra training data)
Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data Augmentation
On Task 1b development data set, we achieve an accuracy of 96. 7\% with a model size smaller than 500KB.
