An Introduction to Restricted Boltzmann Machines
By Asja Fischer, Christian Igel. Iberoamerican Congress on Pattern Recognition, 2012
638 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/dd135a89b5075af5cbef5becaf419457cdd77cc9
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
Citations in the corpus
- Training restricted Boltzmann machines: An introduction (2014, background): “Acknowledgments This article extends our tutorial in [16].”
- An Introductory Review of Deep Learning for Prediction Models With Big Data (2020, background): “The difference between a Restricted Boltzmann Machine and a Boltzmann Machine is that Restricted Boltzmann Machines (RBMs) have constraints in the connectivity of their structure ( Fischer and Igel, 2012).”
- Smart Anomaly Detection in Sensor Systems (2020, background): “Restricted Boltzmann machines (RBM) are bipartite, fully-connected networks, having visible and hidden layers organized in an undirected graph [66].”
- Restricted Boltzmann machine based stock market trend prediction (2017, methodology): “To avoid the exponential complexity of summing over all values of the visible variables (or all values of the hidden if one decides to factorise over the visible variables beforehand), < · >model is usually approximated by samples from the model distribution [10].”
- Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study (2020, background): “Refer to [148], the configuration of the connections between the visible units and the hidden units has an energy function, which can be defined as follow: BackfedInputCell”
- Neural Networks and Deep Learning (2018, neutral): “A discussion and practical suggestions for training Boltzmann machines may be found in [119, 193].”
- Deep Learning in Mining Biological Data (2020, methodology): “Considered as a nonlinear feature detector, [R]BM is trained based on optimizing its parameters for a set of given observations to obtain the best possible fit of the probability distribution through a Markov chain Monte Carlo method known as Gibbs sampling [68, 69].”
- 3-D Deep Learning Approach for Remote Sensing Image Classification (2018, background): “As a remedy for this problem, restrictions were added to the network topology forbidding connections between the variables within the same layer and leading to the one layer restricted Boltzmann machines (RBMs, [11]) as well as its deeper version the Deep Boltzmann machine (DBM).”
- Real-Time Detection of False Data Injection Attacks in Smart Grid: A Deep Learning-Based Intelligent Mechanism (2017, methodology): “widely used deep learning techniques that is constructed with a stack of Restricted Boltzmann Machines (RBMs) [15]–[17].”
- Differentially Private Releasing via Deep Generative Model (2018, methodology): “Second, the method in [12] only works well for low-dimensional data (e.g., 784 for MNIST and 1303 for CDR); in contrast, dp-GAN isable togenerate high-quality, high-dimensional synthetic data (e.g., 12,288 for LSUN).”
- Routing or Computing? The Paradigm Shift Towards Intelligent Computer Network Packet Transmission Based on Deep Learning (2017, background): “RBM is a particular form of log-linear Markov Random Field (MRF) [29].”
- A Review of Deep Learning with Special Emphasis on Architectures, Applications and Recent Trends (2019, background): “Restricted Boltzmann Machine (RBM) [50] can be interpreted as a stochastic neural network.”
- RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach (2016, background): “The deep belief network (DBN) is another deep learning algorithm to learn high-level features from large-scale data [23], which is also a recent popular choice for constructing the computational models.”