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
Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation
Benjamin Scellier,Yoshua Bengio +1 more
TL;DR: In this article, the authors introduce equilibrium propagation, a learning framework for energy-based models that does not need a special computation or circuit for the second phase, where errors are implicitly propagated.
Proceedings ArticleDOI
3D Packing for Self-Supervised Monocular Depth Estimation
TL;DR: Li et al. as mentioned in this paper proposed a self-supervised monocular depth estimation method combining geometry with a new deep network, PackNet, learned only from unlabeled monocular videos, which leverages symmetrical packing and unpacking blocks to jointly learn to compress and decompress detail-preserving representations using 3D convolutions.
Posted Content
Learning Discrete Representations via Information Maximizing Self-Augmented Training
TL;DR: The Information Maximizing Self-Augmented Training (IMSAT) method as mentioned in this paper uses data augmentation to impose the invariance on discrete representations and maximize the information-theoretic dependency between data and their predicted discrete representations.
Posted Content
Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users
TL;DR: This tutorial provides deep learning practitioners with an overview of the relevant literature and a complete toolset to design, implement, train, use and evaluate Bayesian neural networks, i.e., stochastic artificial neural networks trained using Bayesian methods.
Journal ArticleDOI
Systematic evaluation of convolution neural network advances on the Imagenet
TL;DR: It is shown that the use of 128 × 128 pixel images is sufficient to make qualitative conclusions about optimal network structure that hold for the full size Caffe and VGG nets, and an order of magnitude faster than with the standard 224 pixel 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.