中文
相关论文

相关论文: Variational Adaptive Noise and Dropout towards Sta…

200 篇论文

Recurrent Neural networks (RNN) have shown promising potential for learning dynamics of sequential data. However, artificial neural networks are known to exhibit poor robustness in presence of input noise, where the sequential architecture…

机器学习 · 计算机科学 2021-05-05 Arash Amini , Guangyi Liu , Nader Motee

Recurrent Neural Networks (RNNs) are rich models for the processing of sequential data. Recent work on advancing the state of the art has been focused on the optimization or modelling of RNNs, mostly motivated by adressing the problems of…

Approximate inference in Bayesian deep networks exhibits a dilemma of how to yield high fidelity posterior approximations while maintaining computational efficiency and scalability. We tackle this challenge by introducing a novel…

机器学习 · 计算机科学 2021-11-01 Son Nguyen , Duong Nguyen , Khai Nguyen , Khoat Than , Hung Bui , Nhat Ho

This paper proposes to generalize the variational recurrent neural network (RNN) with variational inference (VI)-based dropout regularization employed for the long short-term memory (LSTM) cells to more advanced RNN architectures like gated…

计算与语言 · 计算机科学 2020-09-03 Jun Qi , Xu Liu , Javier Tejedor

Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training. It has been explored for: I. Constructing nested nets: the nested nets are neural…

机器学习 · 计算机科学 2022-06-20 Yufei Cui , Yu Mao , Ziquan Liu , Qiao Li , Antoni B. Chan , Xue Liu , Tei-Wei Kuo , Chun Jason Xue

In this paper, the traditional model based variational method and learning based algorithms are naturally integrated to address mixed noise removal problem. To be different from single type noise (e.g. Gaussian) removal, it is a challenge…

计算机视觉与模式识别 · 计算机科学 2018-05-22 Faqiang Wang , Haiyang Huang , Jun Liu

Feed-forward neural networks (FFNNs) are vulnerable to input noise, reducing prediction performance. Existing regularization methods like dropout often alter network architecture or overlook neuron interactions. This study aims to enhance…

神经与进化计算 · 计算机科学 2025-07-28 Maria Zaitseva , Ivan Tomilov , Natalia Gusarova

Marginalising out uncertain quantities within the internal representations or parameters of neural networks is of central importance for a wide range of learning techniques, such as empirical, variational or full Bayesian methods. We set…

机器学习 · 统计学 2015-07-21 Justin Bayer , Maximilian Karl , Daniela Korhammer , Patrick van der Smagt

Real-world time series data exhibit non-stationary behavior, regime shifts, and temporally varying noise (heteroscedastic) that degrade the robustness of standard regression models. We introduce the Variability-Aware Recursive Neural…

机器学习 · 计算机科学 2025-10-13 Haroon Gharwi , Kai Shu

Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs). Dropout techniques for RNNs were introduced to respond to these demands, but we…

机器学习 · 计算机科学 2019-04-23 Sungrae Park , Kyungwoo Song , Mingi Ji , Wonsung Lee , Il-Chul Moon

We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states. Specifically, we consider RNNs that can be viewed as discretizations of stochastic differential equations driven by…

机器学习 · 统计学 2021-12-02 Soon Hoe Lim , N. Benjamin Erichson , Liam Hodgkinson , Michael W. Mahoney

We introduce Noise Injection Node Regularization (NINR), a method of injecting structured noise into Deep Neural Networks (DNN) during the training stage, resulting in an emergent regularizing effect. We present theoretical and empirical…

机器学习 · 计算机科学 2023-05-03 Noam Levi , Itay M. Bloch , Marat Freytsis , Tomer Volansky

Neural Differential Equations (NDEs) excel at modeling continuous-time dynamics, effectively handling challenges such as irregular observations, missing values, and noise. Despite their advantages, NDEs face a fundamental challenge in…

机器学习 · 统计学 2025-11-19 Jonghun Lee , YongKyung Oh , Sungil Kim , Dong-Young Lim

A core technology that has emerged from the artificial intelligence revolution is the recurrent neural network (RNN). Its unique sequence-based architecture provides a tractable likelihood estimate with stable training paradigms, a…

无序系统与神经网络 · 物理学 2020-07-01 Mohamed Hibat-Allah , Martin Ganahl , Lauren E. Hayward , Roger G. Melko , Juan Carrasquilla

In recurrent neural networks (RNNs) used to model biological neural networks, noise is typically introduced during training to emulate biological variability and regularize learning. The expectation is that removing the noise at test time…

神经与进化计算 · 计算机科学 2026-01-09 Noah Eckstein , Manoj Srinivasan

Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization…

机器学习 · 计算机科学 2024-12-10 Yao Lyu , Xiangteng Zhang , Shengbo Eben Li , Jingliang Duan , Letian Tao , Qing Xu , Lei He , Keqiang Li

Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential prediction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A…

机器学习 · 统计学 2018-03-29 Konrad Zolna , Devansh Arpit , Dendi Suhubdy , Yoshua Bengio

The recurrent neural networks (RNN) with richly distributed internal states and flexible non-linear transition functions, have overtaken the dynamic Bayesian networks such as the hidden Markov models (HMMs) in the task of modeling highly…

机器学习 · 计算机科学 2021-08-11 Jin Huang , Ming Xiao

Recurrent neural networks (RNNs) are powerful models of sequential data. They have been successfully used in domains such as text and speech. However, RNNs are susceptible to overfitting; regularization is important. In this paper we…

机器学习 · 统计学 2018-07-16 Adji B. Dieng , Rajesh Ranganath , Jaan Altosaar , David M. Blei

Dropout is a regularization technique widely used in training artificial neural networks to mitigate overfitting. It consists of dynamically deactivating subsets of the network during training to promote more robust representations. Despite…

机器学习 · 统计学 2025-09-10 Francesco Mori , Francesca Mignacco
‹ 上一页 1 2 3 10 下一页 ›