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
Journal ArticleDOI
Deep Multi-View Enhancement Hashing for Image Retrieval
TL;DR: Zhang et al. as discussed by the authors proposed a supervised multi-view hash model which can enhance the multiview information through neural networks, and the proposed method utilizes an effective view stability evaluation method to actively explore the relationship among views, which will affect the optimization direction of the entire network.
Journal ArticleDOI
A Robust Deep Model for Improved Classification of AD/MCI Patients
TL;DR: A robust deep learning system to identify different progression stages of AD patients based on MRI and PET scans is presented and the dropout technique is utilized to improve classical deep learning by preventing its weight coadaptation, which is a typical cause of overfitting in deep learning.
Proceedings ArticleDOI
Detecting Cyber Attacks in Industrial Control Systems Using Convolutional Neural Networks
Moshe Kravchik,Asaf Shabtai +1 more
TL;DR: 1D convolutional networks can be successfully used for anomaly detection in industrial control systems and outperform recurrent networks in this setting and are effective at time series prediction tasks which are traditionally considered to be best solved using recurrent neural networks.
Journal ArticleDOI
Systematic classification of unknown metabolites using high-resolution fragmentation mass spectra
Kai Dührkop,Louis-Félix Nothias,Markus Fleischauer,Raphael Reher,Marcus Ludwig,Martin Hoffmann,Martin Hoffmann,Daniel Petras,Daniel Petras,William H. Gerwick,William H. Gerwick,Juho Rousu,Pieter C. Dorrestein,Sebastian Böcker +13 more
TL;DR: The broad utility of CANOPUS is demonstrated by investigating the effect of microbial colonization in the mouse digestive system, through analysis of the chemodiversity of different Euphorbia plants and regarding the discovery of a marine natural product, revealing biological insights at the compound class level.
Proceedings ArticleDOI
Adversarial Feature Augmentation for Unsupervised Domain Adaptation
TL;DR: In this article, a feature generator trained by playing the GAN minimax game against source features is used to enforce domain-invariance and perform feature augmentation in unsupervised domain adaptation.
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.