Artigos de revistas: "Machines de Boltzmann restreintes"

1

Apolloni, B., A. Bertoni, P. Campadelli e D. de Falco. "Asymmetric Boltzmann machines". Biological Cybernetics 66, n.º 1 (novembro de 1991): 61–70. http://dx.doi.org/10.1007/bf00196453.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

2

Lu, Wenhao, Chi-Sing Leung e John Sum. "Analysis on Noisy Boltzmann Machines and Noisy Restricted Boltzmann Machines". IEEE Access 9 (2021): 112955–65. http://dx.doi.org/10.1109/access.2021.3102275.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

3

Livesey, M. "Clamping in Boltzmann machines". IEEE Transactions on Neural Networks 2, n.º 1 (1991): 143–48. http://dx.doi.org/10.1109/72.80301.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

4

Fischer, Asja. "Training Restricted Boltzmann Machines". KI - Künstliche Intelligenz 29, n.º 4 (12 de maio de 2015): 441–44. http://dx.doi.org/10.1007/s13218-015-0371-2.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

5

Bojnordi, Mahdi Nazm, e Engin Ipek. "The Memristive Boltzmann Machines". IEEE Micro 37, n.º 3 (2017): 22–29. http://dx.doi.org/10.1109/mm.2017.53.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

6

Liu, Jeremy, Ke-Thia Yao e Federico Spedalieri. "Dynamic Topology Reconfiguration of Boltzmann Machines on Quantum Annealers". Entropy 22, n.º 11 (24 de outubro de 2020): 1202. http://dx.doi.org/10.3390/e22111202.

Texto completo da fonte

Resumo:

Boltzmann machines have useful roles in deep learning applications, such as generative data modeling, initializing weights for other types of networks, or extracting efficient representations from high-dimensional data. Most Boltzmann machines use restricted topologies that exclude looping connectivity, as such connectivity creates complex distributions that are difficult to sample. We have used an open-system quantum annealer to sample from complex distributions and implement Boltzmann machines with looping connectivity. Further, we have created policies mapping Boltzmann machine variables to the quantum bits of an annealer. These policies, based on correlation and entropy metrics, dynamically reconfigure the topology of Boltzmann machines during training and improve performance.

Estilos ABNT, Harvard, Vancouver, APA, etc.

7

Luo, Heng, Ruimin Shen, Changyong Niu e Carsten Ullrich. "Sparse Group Restricted Boltzmann Machines". Proceedings of the AAAI Conference on Artificial Intelligence 25, n.º 1 (4 de agosto de 2011): 429–34. http://dx.doi.org/10.1609/aaai.v25i1.7923.

Texto completo da fonte

Resumo:

Since learning in Boltzmann machines is typically quite slow, there is a need to restrict connections within hidden layers. However, theresulting states of hidden units exhibit statistical dependencies. Based on this observation, we propose using l1/l2 regularization upon the activation probabilities of hidden units in restricted Boltzmann machines to capture the local dependencies among hidden units. This regularization not only encourages hidden units of many groups to be inactive given observed data but also makes hidden units within a group compete with each other for modeling observed data. Thus, the l1/l2 regularization on RBMs yields sparsity at both the group and the hidden unit levels. We call RBMs trained with the regularizer sparse group RBMs (SGRBMs). The proposed SGRBMs are appliedto model patches of natural images, handwritten digits and OCR English letters. Then to emphasize that SGRBMs can learn more discriminative features we applied SGRBMs to pretrain deep networks for classification tasks. Furthermore, we illustrate the regularizer can also be applied to deep Boltzmann machines, which lead to sparse group deep Boltzmann machines. When adapted to the MNIST data set, a two-layer sparse group Boltzmann machine achieves an error rate of 0.84%, which is, to our knowledge, the best published result on the permutation-invariant version of the MNIST task.

Estilos ABNT, Harvard, Vancouver, APA, etc.

8

Decelle, Aurélien, e Cyril Furtlehner. "Gaussian-spherical restricted Boltzmann machines". Journal of Physics A: Mathematical and Theoretical 53, n.º 18 (16 de abril de 2020): 184002. http://dx.doi.org/10.1088/1751-8121/ab79f3.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

9

Apolloni, B., e D. de Falco. "Learning by parallel Boltzmann machines". IEEE Transactions on Information Theory 37, n.º 4 (julho de 1991): 1162–65. http://dx.doi.org/10.1109/18.87009.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

10

d'Anjou, A., M. Grana, F. J. Torrealdea e M. C. Hernandez. "Solving satisfiability via Boltzmann machines". IEEE Transactions on Pattern Analysis and Machine Intelligence 15, n.º 5 (maio de 1993): 514–21. http://dx.doi.org/10.1109/34.211473.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

11

Ticknor, Anthony J., e Harrison H. Barrett. "Optical Implementations In Boltzmann Machines". Optical Engineering 26, n.º 1 (1 de janeiro de 1987): 260116. http://dx.doi.org/10.1117/12.7974015.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

12

Amari, S., K. Kurata e H. Nagaoka. "Information geometry of Boltzmann machines". IEEE Transactions on Neural Networks 3, n.º 2 (março de 1992): 260–71. http://dx.doi.org/10.1109/72.125867.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

13

Welling, Max, e Yee Whye Teh. "Approximate inference in Boltzmann machines". Artificial Intelligence 143, n.º 1 (janeiro de 2003): 19–50. http://dx.doi.org/10.1016/s0004-3702(02)00361-2.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

14

Prager, R. W., T. D. Harrison e F. Fallside. "Boltzmann machines for speech recognition". Computer Speech & Language 1, n.º 1 (março de 1986): 3–27. http://dx.doi.org/10.1016/s0885-2308(86)80008-0.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

15

Balzer, Wolfgang, Masanobu Takahashi, Jun Ohta e Kazuo Kyuma. "Weight quantization in Boltzmann machines". Neural Networks 4, n.º 3 (janeiro de 1991): 405–9. http://dx.doi.org/10.1016/0893-6080(91)90077-i.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

16

Passos, Leandro Aparecido, e João Paulo Papa. "Temperature-Based Deep Boltzmann Machines". Neural Processing Letters 48, n.º 1 (8 de setembro de 2017): 95–107. http://dx.doi.org/10.1007/s11063-017-9707-2.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

17

KOBAYASHI, M. "Boltzmann Machines with Identified States". IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E91-A, n.º 3 (1 de março de 2008): 887–90. http://dx.doi.org/10.1093/ietfec/e91-a.3.887.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

18

Miasnikof, Pierre, Mohammad Bagherbeik e Ali Sheikholeslami. "Graph clustering with Boltzmann machines". Discrete Applied Mathematics 343 (janeiro de 2024): 208–23. http://dx.doi.org/10.1016/j.dam.2023.10.012.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

19

Liu, Kai, Li Min Zhang e Yong Wei Sun. "Deep Boltzmann Machines Aided Design Based on Genetic Algorithms". Applied Mechanics and Materials 568-570 (junho de 2014): 848–51. http://dx.doi.org/10.4028/www.scientific.net/amm.568-570.848.

Texto completo da fonte

Resumo:

To resolve the problem of no guidance about how to set the values of numerical meta-parameters and difficulty to achieve optimization of Deep Boltzmann Machines, genetic algorithms are used to develop an automatic optimizing method named GA-RBMs (Genetic Algorithm-Restricted Boltzmann Machines) for this model’s aided design. Based on the Restricted Boltzmann Machines’ features and evaluation function, a genetic algorithm is designed and realizes the global search of satisfied structure. We also initialize the network’s weights to determine the number of visible units and hidden units. The experiments were conducted on MNIST digits handwritten datasets. The results proved that this optimization reduced the dimension of visible units and improved the performance of feature extracted by Deep Boltzmann Machines. The network optimized has good generalization performance and meets the demand of Deep Boltzmann Machines’ aided design.

Estilos ABNT, Harvard, Vancouver, APA, etc.

20

Saul, Lawrence, e Michael I. Jordan. "Learning in Boltzmann Trees". Neural Computation 6, n.º 6 (novembro de 1994): 1174–84. http://dx.doi.org/10.1162/neco.1994.6.6.1174.

Texto completo da fonte

Resumo:

We introduce a large family of Boltzmann machines that can be trained by standard gradient descent. The networks can have one or more layers of hidden units, with tree-like connectivity. We show how to implement the supervised learning algorithm for these Boltzmann machines exactly, without resort to simulated or mean-field annealing. The stochastic averages that yield the gradients in weight space are computed by the technique of decimation. We present results on the problems of N-bit parity and the detection of hidden symmetries.

Estilos ABNT, Harvard, Vancouver, APA, etc.

21

Yasuda, Muneki, e Kazuyuki Tanaka. "Approximate Learning Algorithm in Boltzmann Machines". Neural Computation 21, n.º 11 (novembro de 2009): 3130–78. http://dx.doi.org/10.1162/neco.2009.08-08-844.

Texto completo da fonte

Resumo:

Boltzmann machines can be regarded as Markov random fields. For binary cases, they are equivalent to the Ising spin model in statistical mechanics. Learning systems in Boltzmann machines are one of the NP-hard problems. Thus, in general we have to use approximate methods to construct practical learning algorithms in this context. In this letter, we propose new and practical learning algorithms for Boltzmann machines by using the belief propagation algorithm and the linear response approximation, which are often referred as advanced mean field methods. Finally, we show the validity of our algorithm using numerical experiments.

Estilos ABNT, Harvard, Vancouver, APA, etc.

22

Crawford, Daniel, Anna Levit, Navid Ghadermarzy, Jaspreet S. Oberoi e Pooya Ronagh. "Reinforcement learning using quantum Boltzmann machines". Quantum Information and Computation 18, n.º 1&2 (fevereiro de 2018): 51–74. http://dx.doi.org/10.26421/qic18.1-2-3.

Texto completo da fonte

Resumo:

We investigate whether quantum annealers with select chip layouts can outperform classical computers in reinforcement learning tasks. We associate a transverse field Ising spin Hamiltonian with a layout of qubits similar to that of a deep Boltzmann machine (DBM) and use simulated quantum annealing (SQA) to numerically simulate quantum sampling from this system. We design a reinforcement learning algorithm in which the set of visible nodes representing the states and actions of an optimal policy are the first and last layers of the deep network. In absence of a transverse field, our simulations show that DBMs are trained more effectively than restricted Boltzmann machines (RBM) with the same number of nodes. We then develop a framework for training the network as a quantum Boltzmann machine (QBM) in the presence of a significant transverse field for reinforcement learning. This method also outperforms the reinforcement learning method that uses RBMs.

Estilos ABNT, Harvard, Vancouver, APA, etc.

23

Kobayashi, Masaki. "Information geometry of rotor Boltzmann machines". Nonlinear Theory and Its Applications, IEICE 7, n.º 2 (2016): 266–82. http://dx.doi.org/10.1587/nolta.7.266.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

24

Yasuda, Muneki, e Tomoyuki Obuchi. "Empirical Bayes method for Boltzmann machines". Journal of Physics A: Mathematical and Theoretical 53, n.º 1 (10 de dezembro de 2019): 014004. http://dx.doi.org/10.1088/1751-8121/ab57a7.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

25

Genovese, Giuseppe, e Daniele Tantari. "Legendre equivalences of spherical Boltzmann machines". Journal of Physics A: Mathematical and Theoretical 53, n.º 9 (4 de fevereiro de 2020): 094001. http://dx.doi.org/10.1088/1751-8121/ab6b92.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

26

Melko, Roger G., Giuseppe Carleo, Juan Carrasquilla e J. Ignacio Cirac. "Restricted Boltzmann machines in quantum physics". Nature Physics 15, n.º 9 (24 de junho de 2019): 887–92. http://dx.doi.org/10.1038/s41567-019-0545-1.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

27

Ackley, David H., Geoffrey E. Hinton e Terrence J. Sejnowski. "A Learning Algorithm for Boltzmann Machines*". Cognitive Science 9, n.º 1 (janeiro de 1985): 147–69. http://dx.doi.org/10.1207/s15516709cog0901_7.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

28

Apolloni, Bruno, e Diego de Falco. "Learning by Asymmetric Parallel Boltzmann Machines". Neural Computation 3, n.º 3 (setembro de 1991): 402–8. http://dx.doi.org/10.1162/neco.1991.3.3.402.

Texto completo da fonte

Resumo:

We consider the Little, Shaw, Vasudevan model as a parallel asymmetric Boltzmann machine, in the sense that we extend to this model the entropic learning rule first studied by Ackley, Hinton, and Sejnowski in the case of a sequentially activated network with symmetric synaptic matrix. The resulting Hebbian learning rule for the parallel asymmetric model draws the signal for the updating of synaptic weights from time averages of the discrepancy between expected and actual transitions along the past history of the network. As we work without the hypothesis of symmetry of the weights, we can include in our analysis also feedforward networks, for which the entropic learning rule turns out to be complementary to the error backpropagation rule, in that it “rewards the correct behavior” instead of “penalizing the wrong answers.”

Estilos ABNT, Harvard, Vancouver, APA, etc.

29

Zhang, Jian, Shifei Ding, Nan Zhang e Weikuan Jia. "Adversarial Training Methods for Boltzmann Machines". IEEE Access 8 (2020): 4594–604. http://dx.doi.org/10.1109/access.2019.2962758.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

30

Fischer, Asja, e Christian Igel. "Training restricted Boltzmann machines: An introduction". Pattern Recognition 47, n.º 1 (janeiro de 2014): 25–39. http://dx.doi.org/10.1016/j.patcog.2013.05.025.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

31

Zhang, Nan, Shifei Ding, Jian Zhang e Yu Xue. "An overview on Restricted Boltzmann Machines". Neurocomputing 275 (janeiro de 2018): 1186–99. http://dx.doi.org/10.1016/j.neucom.2017.09.065.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

32

Schulz, Hannes, Andreas Müller e Sven Behnke. "Exploiting local structure in Boltzmann machines". Neurocomputing 74, n.º 9 (abril de 2011): 1411–17. http://dx.doi.org/10.1016/j.neucom.2010.12.014.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

33

Kappen, Hilbert J. "Deterministic learning rules for boltzmann machines". Neural Networks 8, n.º 4 (janeiro de 1995): 537–48. http://dx.doi.org/10.1016/0893-6080(94)00112-y.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

34

Zwietering, Patrick, e Emile Aarts. "Parallel Boltzmann machines: A mathematical model". Journal of Parallel and Distributed Computing 13, n.º 1 (setembro de 1991): 65–75. http://dx.doi.org/10.1016/0743-7315(91)90110-u.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

35

Aarts, Emile H. L., e Jan H. M. Korst. "Boltzmann machines for travelling salesman problems". European Journal of Operational Research 39, n.º 1 (março de 1989): 79–95. http://dx.doi.org/10.1016/0377-2217(89)90355-x.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

36

Upadhya, Vidyadhar, e P. S. Sastry. "An Overview of Restricted Boltzmann Machines". Journal of the Indian Institute of Science 99, n.º 2 (18 de fevereiro de 2019): 225–36. http://dx.doi.org/10.1007/s41745-019-0102-z.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

37

Cheng, Song, Jing Chen e Lei Wang. "Information Perspective to Probabilistic Modeling: Boltzmann Machines versus Born Machines". Entropy 20, n.º 8 (7 de agosto de 2018): 583. http://dx.doi.org/10.3390/e20080583.

Texto completo da fonte

Resumo:

We compare and contrast the statistical physics and quantum physics inspired approaches for unsupervised generative modeling of classical data. The two approaches represent probabilities of observed data using energy-based models and quantum states, respectively. Classical and quantum information patterns of the target datasets therefore provide principled guidelines for structural design and learning in these two approaches. Taking the Restricted Boltzmann Machines (RBM) as an example, we analyze the information theoretical bounds of the two approaches. We also estimate the classical mutual information of the standard MNIST datasets and the quantum Rényi entropy of corresponding Matrix Product States (MPS) representations. Both information measures are much smaller compared to their theoretical upper bound and exhibit similar patterns, which imply a common inductive bias of low information complexity. By comparing the performance of RBM with various architectures on the standard MNIST datasets, we found that the RBM with local sparse connection exhibit high learning efficiency, which supports the application of tensor network states in machine learning problems.

Estilos ABNT, Harvard, Vancouver, APA, etc.

38

Teng, Da, Zhang Li, Guanghong Gong e Liang Han. "Boltzmann machines with clusters of stochastic binary units". International Journal of Modeling, Simulation, and Scientific Computing 07, n.º 02 (junho de 2016): 1650018. http://dx.doi.org/10.1142/s1793962316500185.

Texto completo da fonte

Resumo:

The original restricted Boltzmann machines (RBMs) are extended by replacing the binary visible and hidden variables with clusters of binary units, and a new learning algorithm for training deep Boltzmann machine of this new variant is proposed. The sum of binary units of each cluster is approximated by a Gaussian distribution. Experiments demonstrate that the proposed Boltzmann machines can achieve good performance in the MNIST handwritten digital recognition task.

Estilos ABNT, Harvard, Vancouver, APA, etc.

39

Salakhutdinov, Ruslan, e Geoffrey Hinton. "An Efficient Learning Procedure for Deep Boltzmann Machines". Neural Computation 24, n.º 8 (agosto de 2012): 1967–2006. http://dx.doi.org/10.1162/neco_a_00311.

Texto completo da fonte

Resumo:

We present a new learning algorithm for Boltzmann machines that contain many layers of hidden variables. Data-dependent statistics are estimated using a variational approximation that tends to focus on a single mode, and data-independent statistics are estimated using persistent Markov chains. The use of two quite different techniques for estimating the two types of statistic that enter into the gradient of the log likelihood makes it practical to learn Boltzmann machines with multiple hidden layers and millions of parameters. The learning can be made more efficient by using a layer-by-layer pretraining phase that initializes the weights sensibly. The pretraining also allows the variational inference to be initialized sensibly with a single bottom-up pass. We present results on the MNIST and NORB data sets showing that deep Boltzmann machines learn very good generative models of handwritten digits and 3D objects. We also show that the features discovered by deep Boltzmann machines are a very effective way to initialize the hidden layers of feedforward neural nets, which are then discriminatively fine-tuned.

Estilos ABNT, Harvard, Vancouver, APA, etc.

40

Suykens, Johan A. K. "Deep Restricted Kernel Machines Using Conjugate Feature Duality". Neural Computation 29, n.º 8 (agosto de 2017): 2123–63. http://dx.doi.org/10.1162/neco_a_00984.

Texto completo da fonte

Resumo:

The aim of this letter is to propose a theory of deep restricted kernel machines offering new foundations for deep learning with kernel machines. From the viewpoint of deep learning, it is partially related to restricted Boltzmann machines, which are characterized by visible and hidden units in a bipartite graph without hidden-to-hidden connections and deep learning extensions as deep belief networks and deep Boltzmann machines. From the viewpoint of kernel machines, it includes least squares support vector machines for classification and regression, kernel principal component analysis (PCA), matrix singular value decomposition, and Parzen-type models. A key element is to first characterize these kernel machines in terms of so-called conjugate feature duality, yielding a representation with visible and hidden units. It is shown how this is related to the energy form in restricted Boltzmann machines, with continuous variables in a nonprobabilistic setting. In this new framework of so-called restricted kernel machine (RKM) representations, the dual variables correspond to hidden features. Deep RKM are obtained by coupling the RKMs. The method is illustrated for deep RKM, consisting of three levels with a least squares support vector machine regression level and two kernel PCA levels. In its primal form also deep feedforward neural networks can be trained within this framework.

Estilos ABNT, Harvard, Vancouver, APA, etc.

41

Kobayashi, Masaki. "Information geometry of hyperbolic-valued Boltzmann machines". Neurocomputing 431 (março de 2021): 163–68. http://dx.doi.org/10.1016/j.neucom.2020.12.048.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

42

YASUDA, Muneki, e Kazuyuki TANAKA. "Boltzmann Machines with Bounded Continuous Random Variables". Interdisciplinary Information Sciences 13, n.º 1 (2007): 25–31. http://dx.doi.org/10.4036/iis.2007.25.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

43

Mohan, Ankith, Aiichiro Nakano e Emilio Ferrara. "Graph signal recovery using restricted Boltzmann machines". Expert Systems with Applications 185 (dezembro de 2021): 115635. http://dx.doi.org/10.1016/j.eswa.2021.115635.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

44

Giuffrida, Mario Valerio, e Sotirios A. Tsaftaris. "Unsupervised Rotation Factorization in Restricted Boltzmann Machines". IEEE Transactions on Image Processing 29 (2020): 2166–75. http://dx.doi.org/10.1109/tip.2019.2946455.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

45

Apolloni, Bruno, Egidio Battistini e Diego de Falco. "Higher-order Boltzmann machines and entropy bounds". Journal of Physics A: Mathematical and General 32, n.º 30 (20 de julho de 1999): 5529–38. http://dx.doi.org/10.1088/0305-4470/32/30/301.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

46

Li, Qing, Yang Chen e Yongjune Kim. "Compression by and for Deep Boltzmann Machines". IEEE Transactions on Communications 68, n.º 12 (dezembro de 2020): 7498–510. http://dx.doi.org/10.1109/tcomm.2020.3020796.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

47

Bounds, D. G. "A statistical mechanical study of Boltzmann machines". Journal of Physics A: Mathematical and General 20, n.º 8 (1 de junho de 1987): 2133–45. http://dx.doi.org/10.1088/0305-4470/20/8/027.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

48

Azencott, Robert, Antoine Doutriaux e Laurent Younes. "Synchronous Boltzmann machines and curve identification tasks*". Network: Computation in Neural Systems 4, n.º 4 (1 de novembro de 1993): 461–80. http://dx.doi.org/10.1088/0954-898x/4/4/004.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

49

Azencott, Robert, Antoine Doutriaux e Laurent Younes. "Synchronous Boltzmann machines and curve identification tasks". Network: Computation in Neural Systems 4, n.º 4 (janeiro de 1993): 461–80. http://dx.doi.org/10.1088/0954-898x_4_4_004.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

50

Neal, Radford M. "Asymmetric Parallel Boltzmann Machines are Belief Networks". Neural Computation 4, n.º 6 (novembro de 1992): 832–34. http://dx.doi.org/10.1162/neco.1992.4.6.832.

Texto completo da fonte

Estilos ABNT, Harvard, Vancouver, APA, etc.

Artigos de revistas sobre o tema "Machines de Boltzmann restreintes"

Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos