Results 21 to 30 of about 118,488 (274)

A Bayesian Neural Network based on Dropout Regulation

CoRR, 2020
Bayesian Neural Networks (BNN) have recently emerged in the Deep Learning world for dealing with uncertainty estimation in classification tasks, and are used in many application domains such as astrophysics, autonomous driving...BNN assume a prior over the weights of a neural network instead of point estimates, enabling in this way the estimation of ...
Theobald, Claire, Pennerath, Frédéric, Conan-Guez, Brieuc, Couceiro, Miguel, Napoli, Amedeo   +4 more
openaire   +3 more sources

Variational Bayesian dropout with a Gaussian prior for recurrent neural networks application in rainfall–runoff modeling

Environmental Research Letters, 2022
Recurrent neural networks (RNNs) are a class of artificial neural networks capable of learning complicated nonlinear relationships and functions from a set of data.
S Sadeghi Tabas, S Samadi
doaj   +1 more source

Adversarial Dropout for Recurrent Neural Networks

Proceedings of the AAAI Conference on Artificial Intelligence, 2019
Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs). Dropout techniques for RNNs were introduced to respond to these demands, but we conjecture that the dropout on RNNs could have been improved by adopting the adversarial concept.
Sungrae Park, Kyungwoo Song, Mingi Ji, Wonsung Lee, Il-Chul Moon   +4 more
openaire   +3 more sources

DropELM: Fast neural network regularization with Dropout and DropConnect [PDF]

Neurocomputing, 2015
In this paper, we propose an extension of the Extreme Learning Machine algorithm for Single-hidden Layer Feedforward Neural network training that incorporates Dropout and DropConnect regularization in its optimization process. We show that both types of regularization lead to the same solution for the network output weights calculation, which is ...
Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas   +2 more
openaire   +3 more sources

Deep learning approach for predicting university dropout: a case study at Roma Tre University

Je-LKS: Journal of E-Learning and Knowledge Society, 2020
Based on current trends in graduation rates, 39% of todays young adults on average across OECD countries are expected to complete tertiary-type A (university level) education during their lifetime.
Francesco Agrusti, Mauro Mezzini, Gianmarco Bonavolontà   +2 more
doaj   +1 more source

Learning to Balance Local Losses via Meta-Learning

IEEE Access, 2021
The standard training for deep neural networks relies on a global and fixed loss function. For more effective training, dynamic loss functions have been recently proposed.
Seungdong Yoa, Minkyu Jeon, Youngjin Oh, Hyunwoo J. Kim   +3 more
doaj   +1 more source

Dropout in Neural Networks Simulates the Paradoxical Effects of Deep Brain Stimulation on Memory

Frontiers in Aging Neuroscience, 2020
Neuromodulation techniques such as deep brain stimulation (DBS) are a promising treatment for memory-related disorders including anxiety, addiction, and dementia.
Shawn Zheng Kai Tan, Richard Du, Jose Angelo Udal Perucho, Shauhrat S. Chopra, Varut Vardhanabhuti, Lee Wei Lim   +5 more
doaj   +1 more source

Evaluating the Learning Procedure of CNNs through a Sequence of Prognostic Tests Utilising Information Theoretical Measures

Entropy, 2021
Deep learning has proven to be an important element of modern data processing technology, which has found its application in many areas such as multimodal sensor data processing and understanding, data generation and anomaly detection.
Xiyu Shi, Varuna De-Silva, Yusuf Aslan, Erhan Ekmekcioglu, Ahmet Kondoz   +4 more
doaj   +1 more source

Performance of a Novel Chaotic Firefly Algorithm with Enhanced Exploration for Tackling Global Optimization Problems: Application for Dropout Regularization

Mathematics, 2021
Swarm intelligence techniques have been created to respond to theoretical and practical global optimization problems. This paper puts forward an enhanced version of the firefly algorithm that corrects the acknowledged drawbacks of the original method, by
Nebojsa Bacanin, Ruxandra Stoean, Miodrag Zivkovic, Aleksandar Petrovic, Tarik A. Rashid, Timea Bezdan   +5 more
doaj   +1 more source

Skipout: An Adaptive Layer-Level Regularization Framework for Deep Neural Networks

IEEE Access, 2022
Regularization methods can surprisingly improve the generalization ability of deep neural networks. Among numerous methods, the branch of Dropout regularization is very popular in practice.
Hojjat Moayed, Eghbal G. Mansoori
doaj   +1 more source