Results 1 to 10 of about 22,598 (163)
On the quantitative analysis of deep belief networks [PDF]
Proceedings of the 25th international conference on Machine learning - ICML '08, 2008 Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allowed these models to be applied successfully in many application domains. The main building block of a DBN is a bipartite undirected graphical model called a restricted Boltzmann ...
Salakhutdinov, Ruslan, Murray, Iain
openaire +2 more sources
A Developmental Approach for Training Deep Belief Networks
Cognitive Computation, 2022 AbstractDeep belief networks (DBNs) are stochastic neural networks that can extract rich internal representations of the environment from the sensory data. DBNs had a catalytic effect in triggering the deep learning revolution, demonstrating for the very first time the feasibility of unsupervised learning in networks with many layers of hidden neurons.
Matteo Zambra +3 more
openaire +3 more sources
Deep Adversarial Belief Networks
CoRR, 2019 We present a novel adversarial framework for training deep belief networks (DBNs), which includes replacing the generator network in the methodology of generative adversarial networks (GANs) with a DBN and developing a highly parallelizable numerical algorithm for training the resulting architecture in a stochastic manner.
Yuming Huang 0004 +4 more
openaire +2 more sources
Deep Learning and Music Adversaries [PDF]
, 2015 OA Monitor ExerciseOA Monitor ExerciseAn {\em adversary} is essentially an algorithm intent on making a classification system perform in some particular way given an input, e.g., increase the probability of a false negative.
STURM, BLT +5 more
core +1 more source
Learning Deep Belief Networks from Non-Stationary Streams [PDF]
, 2012 18.10.13 KB. Ok to add author version to spiral from LNCS; embargo period expired. SpringerDeep learning has proven to be beneficial for complex tasks such as classifying images. However, this approach has been mostly applied to static datasets.
Pouzols, Federico Montesino +11 more
core +1 more source
The training process of deep belief network model.
, 2023 The training process of deep belief network model.
Yucheng Zhang (136327) +5 more
core +1 more source
Use of Overlapping Group LASSO Sparse Deep Belief Network to Discriminate Parkinson's Disease and Normal Control. [PDF]
Front Neurosci, 2019 As a medical imaging technology which can show the metabolism of the brain, 18F-fluorodeoxyglucose (FDG)-positron emission tomography (PET) is of great value for the diagnosis of Parkinson's Disease (PD).
Shen T +9 more
europepmc +2 more sources
Rock Granularity Analysis by Deep Belief Network [PDF]
, 2017 Granularity analysis is one of the most essential issues in authenticate. To improve the identification accuracy, a Deep Belief Network (DBN) based method is proposed in this paper.
Jiancheng Guo, Guo Wenhui
core +2 more sources
Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2018 Developments in deep learning have seen the use of layerwise unsupervised learning combined with supervised learning for fine-tuning. With this layerwise approach, a deep network can be seen as a more modular system that lends itself well to learning representations.
Son Ngoc Tran, Artur S. d'Avila Garcez
openaire +3 more sources
An Improved Deep Belief Network Prediction Model Based on Knowledge Transfer
, 2020 A deep belief network (DBN) is a powerful generative model based on unlabeled data. However, it is difficult to quickly determine the best network structure and gradient dispersion in traditional DBN.
Fangai Liu, Yue Zhang
core +1 more source