Open AccessJournal Article
Dropout: a simple way to prevent neural networks from overfitting
TLDR
It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.Abstract:
Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.read more
Citations
More filters
Proceedings ArticleDOI
Distinguishing computer graphics from natural images using convolution neural networks
TL;DR: The proposed method uses a Convolutional Neural Network with a custom pooling layer to optimize current best-performing algorithms feature extraction scheme and outperforms state of the art methods for both local and full image classification.
Journal ArticleDOI
Deep learning and artificial intelligence methods for Raman and surface-enhanced Raman scattering
Félix Lussier,Félix Lussier,Vincent Thibault,Benjamin Charron,Gregory Q Wallace,Jean-Francois Masson +5 more
TL;DR: A brief overview of the most common machine learning techniques employed in Raman, a guideline for new users to implement machine learning in their data analysis process, and an overview of modern applications of machine learning of Raman and SERS are provided.
Journal ArticleDOI
$\mathtt {Deepr}$: A Convolutional Net for Medical Records.
TL;DR: A new deep learning system that learns to extract features from medical records and predicts future risk automatically achieves superior accuracy compared to traditional techniques, detects meaningful clinical motifs, and uncovers the underlying structure of the disease and intervention space.
Journal ArticleDOI
Wind Turbine Gearbox Failure Identification With Deep Neural Networks
TL;DR: The feasibility of monitoring the health of wind turbine (WT) gearboxes based on the lubricant pressure data in the supervisory control and data acquisition system is investigated and a deep neural network (DNN)-based framework is developed to monitor conditions of WT gearboxes and identify their impending failures.
Journal ArticleDOI
A transfer learning method with deep residual network for pediatric pneumonia diagnosis.
Gaobo Liang,Lixin Zheng +1 more
TL;DR: A deep learning framework that combines residual thought and dilated convolution to diagnose and detect childhood pneumonia and which can effectively solve the problem of low image resolution and partial occlusion of the inflammatory area in children chest X-ray images.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Regression Shrinkage and Selection via the Lasso
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Journal ArticleDOI
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Dissertation
Learning Multiple Layers of Features from Tiny Images
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.