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
Learning Sequence Encoders for Temporal Knowledge Graph Completion
TL;DR: This work utilizes recurrent neural networks to learn time-aware representations of relation types which can be used in conjunction with existing latent factorization methods to incorporate temporal information.
Proceedings Article
BatchCrypt: Efficient homomorphic encryption for cross-silo federated learning
TL;DR: BatchCrypt is presented, a system solution for cross-silo FL that substantially reduces the encryption and communication overhead caused by HE, and develops new quantization and encoding schemes along with a novel gradient clipping technique.
Journal ArticleDOI
LIDAR–camera fusion for road detection using fully convolutional neural networks
TL;DR: In this article, a deep learning approach was developed to carry out road detection by fusing LIDAR point clouds and camera images, which achieved excellent performance with a MaxF score of 96.03%.
Proceedings Article
Neural Trojans
TL;DR: This work shows that embedding hidden malicious functionality, i.e neural Trojans, into the neural IP is an effective attack and provides three mitigation techniques: input anomaly detection, re-training, and input preprocessing.
Proceedings Article
Using Deep and Convolutional Neural Networks for Accurate Emotion Classification on DEAP Dataset.
TL;DR: This research is a testament that Neural Networks could be robust classifiers for brain signals, even outperforming traditional learning techniques.
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.