Filters








69 Hits in 5.7 sec

Online Deep Learning: Growing RBM on the fly [article]

Savitha Ramasamy, Kanagasabai Rajaraman, Pavitra Krishnaswamy, Vijay Chandrasekhar
2018 arXiv   pre-print
We propose a novel online learning algorithm for Restricted Boltzmann Machines (RBM), namely, the Online Generative Discriminative Restricted Boltzmann Machine (OGD-RBM), that provides the ability to build  ...  The OGD-RBM is trained in two phases: (1) an online generative phase for unsupervised feature representation at the hidden layer and (2) a discriminative phase for classification.  ...  Online Generative Discriminative Restricted Boltzmann Machine We describe the Online Generative Discriminative Restricted Boltzmann Machine (OGD-RBM) learning algorithm.  ... 
arXiv:1803.02043v1 fatcat:5nyh6t7gqrexbpb2adeyh3fyqq

RBM-MHC: A Semi-Supervised Machine-Learning Method for Sample-Specific Prediction of Antigen Presentation by HLA-I Alleles

Barbara Bravi, Jérôme Tubiana, Simona Cocco, Rémi Monasson, Thierry Mora, Aleksandra M. Walczak
2020 Cell Systems  
Here, we introduce a method based on Restricted Boltzmann Machines (RBMs) for prediction of antigens presented on the Major Histocompatibility Complex (MHC) encoded by HLA genes-RBM-MHC.  ...  RBM-MHC ensures improved predictions for rare alleles and matches state-of-the-art performance for well-characterized alleles while being less data demanding.  ...  This material is based upon work supported under a collaboration by Stand Up to Cancer, a program of the Entertainment Industry Foundation, the Society for Immunotherapy of Cancer, and the Lustgarten Foundation  ... 
doi:10.1016/j.cels.2020.11.005 pmid:33338400 pmcid:PMC7895905 fatcat:6tww67brg5duzldrh3b7bwxina

Detection of Unknown Anomalies in Streaming Videos with Generative Energy-based Boltzmann Models [article]

Hung Vu and Tu Dinh Nguyen and Dinh Phung
2018 arXiv   pre-print
Our experiments show that our detectors, using Restricted Boltzmann Machines (RBMs) and Deep Boltzmann Machines (DBMs) as core modules, achieve superior anomaly detection performance to unsupervised baselines  ...  To handle video stream, we develop an online version of our framework, wherein the model parameters are updated incrementally with the image frames arriving on the fly.  ...  Restricted Boltzmann Machines (RBMs) are one of the fundamental energy-based networks with one visible layer and one hidden layer.  ... 
arXiv:1805.01090v2 fatcat:hliv242f6fat7k2ssf77y3lrpq

Improved Gaussian-Bernoulli Restricted Boltzmann Machines for UAV-Ground Communication Systems [article]

Osamah A. Abdullah and Michael C. Batistatos and Hayder Al-Hraishawi
2022 arXiv   pre-print
Specifically, we develop a procedure of multiple Gaussian Bernoulli restricted Boltzmann machines (GBRBM) for dimension reduction and pre-training utilization incorporated with an autoencoder-based deep  ...  Unmanned aerial vehicle (UAV) is steadily growing as a promising technology for next-generation communication systems due to their appealing features such as wide coverage with high altitude, on-demand  ...  It can also learn a probability distribution over a set of inputs in an unsupervised manner and it addresses the limitations of the bipartite restricted Boltzmann machine (RBM) model by replacing the binary  ... 
arXiv:2206.08209v1 fatcat:fsoq7ktkpfafxk4tneerzojhx4

Learning to Represent Spatial Transformations with Factored Higher-Order Boltzmann Machines

Roland Memisevic, Geoffrey E. Hinton
2010 Neural Computation  
To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicative interactions that  ...  We also show how learning about image transformations allows the model to perform a simple visual analogy task, and we show how a completely unsupervised network trained on transformations perceives multiple  ...  We generated the training images on the fly and trained the model online on the resulting stream of image pairs using batches of size 20 to 100 for each gradient update.  ... 
doi:10.1162/neco.2010.01-09-953 pmid:20141471 fatcat:xq2t4g4svvdx7fb324fk7ei6zy

Deep Learning in Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data

Taeho Jo, Kwangsik Nho, Andrew J. Saykin
2019 Frontiers in Aging Neuroscience  
The combination of traditional machine learning for classification and stacked auto-encoder (SAE) for feature selection produced accuracies of up to 98.8% for AD classification and 83.7% for prediction  ...  Deep learning, a state-of-the-art machine learning approach, has shown outstanding performance over traditional machine learning in identifying intricate structures in complex high-dimensional data, especially  ...  The Restricted Boltzmann Machine (RBM) was one of the first models developed to overcome the overfitting problem (Hinton and Salakhutdinov, 2006) .  ... 
doi:10.3389/fnagi.2019.00220 pmid:31481890 pmcid:PMC6710444 fatcat:udknjrow3rf5fkr7bkjcswy3jy

A Comparative Study of AI-based Intrusion Detection Techniques in Critical Infrastructures [article]

Safa Otoum and Burak Kantarci and Hussein Mouftah
2020 arXiv   pre-print
Results present the performance metrics for three different IDSs namely the Adaptively Supervised and Clustered Hybrid IDS (ASCH-IDS), Restricted Boltzmann Machine-based Clustered IDS (RBC-IDS) and Q-learning  ...  The growth of the volume and variety of data traffic in the Internet leads to concerns on the robustness of cyberphysical systems especially for critical infrastructures.  ...  The RBM permits connections between layers: (V) and (H) which refer to the visible and the hidden layers respectively, where the learning Restricted Boltzmann machine (RBM) is a neural, energetic network  ... 
arXiv:2008.00088v1 fatcat:itetvn2n3ratrn4shhvn2tnjiq

Multi-label spacecraft electrical signal classification method based on DBN and random forest

Ke Li, Nan Yu, Pengfei Li, Shimin Song, Yalei Wu, Yang Li, Meng Liu, Zhaohong Deng
2017 PLoS ONE  
Secondly, the deep belief network is used to reduce the feature dimension and improve the rate of classification for the electrical characteristics data.  ...  This paper proposes a feature extraction method that is based on deep belief networks (DBN) and a classification method that is based on the random forest (RF) algorithm; The proposed algorithm mainly  ...  The deep belief network (DBN) is stacked by multiple Restricted Boltzmann machine (RBM) networks, and the output of the last RBM network is the next input [18, 19] .  ... 
doi:10.1371/journal.pone.0176614 pmid:28486479 pmcid:PMC5423585 fatcat:zbw35opg6zhqvnrgtotfpxw3xa

Deep Learning for IoT Big Data and Streaming Analytics: A Survey [article]

Mehdi Mohammadi, Ala Al-Fuqaha, Sameh Sorour, Mohsen Guizani
2018 arXiv   pre-print
In this paper, we provide a thorough overview on using a class of advanced machine learning techniques, namely Deep Learning (DL), to facilitate the analytics and learning in the IoT domain.  ...  DL implementation approaches on the fog and cloud centers in support of IoT applications are also surveyed. Finally, we shed light on some challenges and potential directions for future research.  ...  The restriction in RBMs is applied to the connectivity of neurons compared to Boltzmann machine.  ... 
arXiv:1712.04301v2 fatcat:kr64lst37rhlfcpaxckgzlozvu

Practical Recommendations for Gradient-Based Training of Deep Architectures [chapter]

Yoshua Bengio
2012 Lecture Notes in Computer Science  
This chapter is meant as a practical guide with recommendations for some of the most commonly used hyper-parameters, in particular in the context of learning algorithms based on backpropagated gradient  ...  It also discusses how to deal with the fact that more interesting results can be obtained when allowing one to adjust many hyper-parameters.  ...  Frederic Bastien, and Sina Honari, as well as for the financial support of NSERC, FQRNT, CIFAR, and the Canada Research Chairs.  ... 
doi:10.1007/978-3-642-35289-8_26 fatcat:k6lsp2fxv5ei3efgkmf5p5okyy

Improving Deep Learning through Automatic Programming [article]

The-Hien Dang-Ha
2018 arXiv   pre-print
Therefore, improving the performance of these models could make a strong impact in the area of machine learning.  ...  Based on this knowledge, we suggested, and conducted some experiments to investigate the possibility of improving the deep learning based on automatic programming (ADATE).  ...  Restricted Boltzmann Machines -RBM A RBM is a Boltzmann machine, which is restricted by omitting intra-layer connections (e.g. hidden-hidden and visible-visible connections).  ... 
arXiv:1807.02816v1 fatcat:3qf6jg3xqfcc7ixvu43bz6yvsm

Convergence of Photovoltaic Power Forecasting and Deep Learning: State-of-Art Review

Mohamed Massaoudi, Ines Chihi, Haitham Abu-Rub, Shady S. Refaat, Fakhreddine S. Oueslati
2021 IEEE Access  
RBM (Restricted Boltzmann Machine) network is energy-based stochastic neural networks, as shown in Fig. 8(j) .  ...  These ubiquitous DL architectures are Auto-Encoders (AEs), Restricted Boltzmann Machines (RBMs), and Deep Belief Networks (DBNs), and Generative Adversarial Network, respectively. 1) RBMs and DBN The  ... 
doi:10.1109/access.2021.3117004 fatcat:nxgyb5e4rvbynpmgzppv7ecbre

Practical recommendations for gradient-based training of deep architectures [article]

Yoshua Bengio
2012 arXiv   pre-print
This chapter is meant as a practical guide with recommendations for some of the most commonly used hyper-parameters, in particular in the context of learning algorithms based on back-propagated gradient  ...  It also discusses how to deal with the fact that more interesting results can be obtained when allowing one to adjust many hyper-parameters.  ...  Frederic Bastien, and Sina Honari, as well as for the financial support of NSERC, FQRNT, CIFAR, and the Canada Research Chairs.  ... 
arXiv:1206.5533v2 fatcat:xbtvaaby2jfjjae4hvwyxks7yu

Deep Learning in Smart Grid Technology: A Review of Recent Advancements and Future Prospects

Mohamed Massaoudi, Haitham Abu-Rub, Shady S. Refaat, Ines Chihi, Fakhreddine S. Oueslati
2021 IEEE Access  
Motivated by the outstanding success of DL-based prediction methods, this article attempts to provide a thorough review from a broad perspective on the state-of-the-art advances of DL in SG systems.  ...  This study's core objective is to foster the synergy between these two fields for decision-makers and researchers to accelerate DL's practical deployment for SG systems.  ...  The shallow Boltzmann machine (BM), shown in Fig. 6 (a), is found ineffective for its poor learning potential and high calculation complexities.  ... 
doi:10.1109/access.2021.3071269 fatcat:77gyjqaj2zeznc57r4n7kfbu7e

Machine Learning in Beyond 5G/6G Networks—State-of-the-Art and Future Trends

Vasileios P. Rekkas, Sotirios Sotiroudis, Panagiotis Sarigiannidis, Shaohua Wan, George K. Karagiannidis, Sotirios K. Goudos
2021 Electronics  
Additionally, we discuss open issues in the field of ML for 6G networks and wireless communications in general, as well as some potential future trends to motivate further research into this area.  ...  These methods include supervised, unsupervised and reinforcement techniques.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics10222786 fatcat:6umid7qnabdttkjyhglpxjpwpm
« Previous Showing results 1 — 15 out of 69 results