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
Posted Content
The Lottery Ticket Hypothesis: Training Pruned Neural Networks.
Jonathan Frankle,Michael Carbin +1 more
TL;DR: The lottery ticket hypothesis and its connection to pruning are a step toward developing architectures, initializations, and training strategies that make it possible to solve the same problems with much smaller networks.
Journal ArticleDOI
Modified U-Net (mU-Net) With Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images
TL;DR: In this paper, a residual path with deconvolution and activation operations was added to the skip connection of the U-Net to avoid duplication of low-resolution information of features.
Book ChapterDOI
Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks
TL;DR: The authors introduced an attention-over-attention (AOA) neural network for aspect-level sentiment classification, which jointly learns the representations for aspects and sentences, and automatically focuses on the important parts in sentences.
Journal ArticleDOI
Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology
TL;DR: This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma using the widely known AlexNet deep convolutional framework.
Journal ArticleDOI
Learning Sensor-Specific Spatial-Spectral Features of Hyperspectral Images via Convolutional Neural Networks
TL;DR: The proposed C-CNN outperforms the state-of-the-art CNN-based classification methods, and its corresponding FL-CNN is very effective to extract sensor-specific spatial-spectral features for hyperspectral applications under both supervised and unsupervised modes.
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.