Results 31 to 40 of about 118,488 (274)
Dropout Improves Recurrent Neural Networks for Handwriting Recognition [PDF]
2014 14th International Conference on Frontiers in Handwriting Recognition, 2014 Recurrent neural networks (RNNs) with Long Short-Term memory cells currently hold the best known results in unconstrained handwriting recognition. We show that their performance can be greatly improved using dropout - a recently proposed regularization method for deep architectures.
Vu Pham +3 more
openaire +2 more sources
Adaptive Tabu Dropout for Regularization of Deep Neural Networks
, 2023 Dropout is an effective strategy for the regularization of deep neural networks. Applying tabu to the units that have been dropped in the recent epoch and retaining them for training ensures diversification in dropout. In this paper, we improve the Tabu Dropout mechanism for training deep neural networks in two ways.
Md. Tarek Hasan +6 more
openaire +2 more sources
Prediction of golden time for recovering SISs using deep fuzzy neural networks with rule-dropout
Nuclear Engineering and Technology, 2021 If safety injection systems (SISs) do not work in the event of a loss-of-coolant accident (LOCA), the accident can progress to a severe accident in which the reactor core is exposed and the reactor vessel fails.
Hye Seon Jo +5 more
doaj +1 more source
Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path [PDF]
, 2015 Relation classification is an important research arena in the field of natural language processing (NLP). In this paper, we present SDP-LSTM, a novel neural network to classify the relation of two entities in a sentence. Our neural architecture leverages
Chen, Yunchuan +5 more
core +1 more source
Variational Dropout Sparsifies Deep Neural Networks
CoRR, 2017 Published in ICML ...
Dmitry Molchanov +2 more
openaire +3 more sources
Almost Sure Convergence of Dropout Algorithms for Neural Networks
CoRR, 2020 We investigate the convergence and convergence rate of stochastic training algorithms for Neural Networks (NNs) that have been inspired by Dropout (Hinton et al., 2012). With the goal of avoiding overfitting during training of NNs, dropout algorithms consist in practice of multiplying the weight matrices of a NN componentwise by independently drawn ...
Albert Senen-Cerda, Jaron Sanders
openaire +3 more sources
Predicting Forex Currency Fluctuations Using a Novel Bio-Inspired Modular Neural Network
Big Data and Cognitive Computing, 2023 In the realm of foreign exchange (Forex) market predictions, Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been commonly employed. However, these models often exhibit instability due to vulnerability to data perturbations
Christos Bormpotsis +2 more
doaj +1 more source
Adversarial Dropout for Supervised and Semi-supervised Learning
, 2017 Recently, the training with adversarial examples, which are generated by adding a small but worst-case perturbation on input examples, has been proved to improve generalization performance of neural networks. In contrast to the individually biased inputs
Moon, Il-Chul +3 more
core +1 more source
Improvements to deep convolutional neural networks for LVCSR [PDF]
, 2013 Deep Convolutional Neural Networks (CNNs) are more powerful than Deep Neural Networks (DNN), as they are able to better reduce spectral variation in the input signal.
Aravkin, Aleksandr Y. +8 more
core +1 more source
A Theoretical Analysis of Deep Neural Networks for Texture Classification
, 2016 We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations.
Basu, Saikat +6 more
core +1 more source