Training restricted Boltzmann machines: An introduction
Abstract Restricted Boltzmann machines (RBMs) are probabilistic graphical models that can
be interpreted as stochastic neural networks. They have attracted much attention as building …
be interpreted as stochastic neural networks. They have attracted much attention as building …
An evaluation of the performance of Restricted Boltzmann Machines as a model for anomaly network intrusion detection
T Aldwairi, D Perera, MA Novotny - Computer Networks, 2018 - Elsevier
The continuous increase in the number of attacks on computer networks has raised serious
concerns regarding the importance of establishing a methodology that can learn and adapt …
concerns regarding the importance of establishing a methodology that can learn and adapt …
Fine-tuning deep belief networks using harmony search
In this paper, we deal with the problem of Deep Belief Networks (DBNs) parameters fine-
tuning by means of a fast meta-heuristic approach named Harmony Search (HS). Although …
tuning by means of a fast meta-heuristic approach named Harmony Search (HS). Although …
A fuzzy restricted Boltzmann machine: Novel learning algorithms based on the crisp possibilistic mean value of fuzzy numbers
A fuzzy restricted Boltzmann machine (FRBM) is extended from a restricted Boltzmann
machine (RBM) by replacing all the real-valued parameters with fuzzy numbers. A new …
machine (RBM) by replacing all the real-valued parameters with fuzzy numbers. A new …
Langevin-gradient parallel tempering for Bayesian neural learning
Bayesian inference provides a rigorous approach for neural learning with knowledge
representation via the posterior distribution that accounts for uncertainty quantification …
representation via the posterior distribution that accounts for uncertainty quantification …
[PDF][PDF] Training energy-based models for time-series imputation
Imputing missing values in high dimensional time-series is a difficult problem. This paper
presents a strategy for training energy-based graphical models for imputation directly …
presents a strategy for training energy-based graphical models for imputation directly …
Boltzmann encoded adversarial machines
Restricted Boltzmann Machines (RBMs) are a class of generative neural network that are
typically trained to maximize a log-likelihood objective function. We argue that likelihood …
typically trained to maximize a log-likelihood objective function. We argue that likelihood …
Training restricted boltzmann machine using gradient fixing based algorithm
F LI, X GAO, K WAN - Chinese Journal of Electronics, 2018 - Wiley Online Library
Most of the algorithms for training restricted Boltzmann machines (RBM) are based on Gibbs
sampling. When the sampling algorithm is used to calculate the gradient, the sampling …
sampling. When the sampling algorithm is used to calculate the gradient, the sampling …
[PDF][PDF] 基于动态Gibbs 采样的RBM 训练算法研究
李飞, 高晓光, 万开方 - 自动化学报, 2016 - aas.net.cn
摘要目前大部分受限玻尔兹曼机(Restricted Boltzmann machines, RBMs) 训练算法都是以多步
Gibbs 采样为基础的采样算法. 本文针对多步Gibbs 采样过程中出现的采样发散和训练速度过慢 …
Gibbs 采样为基础的采样算法. 本文针对多步Gibbs 采样过程中出现的采样发散和训练速度过慢 …
[PDF][PDF] Multi-Document Text Summarization Using Deep Belief Network
AM Abid - International Journal of Advances in Scientific …, 2022 - academia.edu
Recently, there is a lot of information available on the Internet, which makes it difficult for
users to find what they're looking for. Extractive text summarization methods are designed to …
users to find what they're looking for. Extractive text summarization methods are designed to …