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
A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
TL;DR: The authors introduce a joint many-task model together with a strategy for successively growing its depth to solve increasingly complex tasks, and use a simple regularization term to allow for optimizing all model weights to improve one task's loss without exhibiting catastrophic interference of the other tasks.
Journal ArticleDOI
Minerva: enabling low-power, highly-accurate deep neural network accelerators
Brandon Reagen,Paul N. Whatmough,Robert Adolf,Saketh Rama,Hyunkwang Lee,Sae Kyu Lee,José Miguel Hernández-Lobato,Gu-Yeon Wei,David Brooks +8 more
TL;DR: Minerva as mentioned in this paper proposes a co-design approach across the algorithm, architecture, and circuit levels to optimize DNN hardware accelerators, and shows that fine-grained, heterogeneous dataatype optimization reduces power by 1.5× and aggressive, inline predication and pruning of small activity values further reduces power.
Proceedings ArticleDOI
MesoNet: a Compact Facial Video Forgery Detection Network
TL;DR: In this article, a method to automatically and efficiently detect face tampering in videos, and particularly focusing on two recent techniques used to generate hyper-realistic forged videos: Deepfake and Face2Face, is presented.
Supplementary Material for Human-level concept learning through probabilistic program induction
TL;DR: The authors presented a computational model that captures human learning abilities for a large class of simple visual concepts: handwritten characters from the world's alphabets, represented as simple programs that best explain observed examples under a Bayesian criterion.
Proceedings Article
How does batch normalization help optimization
TL;DR: In this article, the authors uncover a more fundamental impact of batch normalization on the training process: it makes the optimization landscape significantly smoother, which induces a more predictive and stable behavior of the gradients, allowing for faster training.
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.