Open AccessProceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
Reads0
Chats0
TLDR
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.Abstract:
We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.read more
Citations
More filters
Proceedings ArticleDOI
In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking
TL;DR: This work describes a new method to expose fake face videos generated with deep neural network models based on detection of eye blinking in the videos, which is a physiological signal that is not well presented in the synthesized fake videos.
Journal ArticleDOI
Multiscale Convolutional Neural Networks for Fault Diagnosis of Wind Turbine Gearbox
TL;DR: Experimental results and comprehensive comparison analysis have demonstrated the superiority of the proposed MSCNN approach, thus providing an end-to-end learning-based fault diagnosis system for WT gearbox without additional signal processing and diagnostic expertise.
Proceedings Article
Adafactor: Adaptive Learning Rates with Sublinear Memory Cost
Noam Shazeer,Mitchell Stern +1 more
TL;DR: In this paper, the authors propose to estimate the per-parameter second moments based on the inverse square roots of exponential moving averages of squared past gradients of neural network weight matrices and show that adaptive methods can produce larger-than-desired updates when the decay rate of the second moment accumulator is too slow.
Proceedings Article
One-Shot Imitation Learning
Yan Duan,Marcin Andrychowicz,Bradly C. Stadie,OpenAI Jonathan Ho,Jonas Schneider,Ilya Sutskever,Pieter Abbeel,Wojciech Zaremba +7 more
TL;DR: One-shot imitation learning as mentioned in this paper is a meta-learning framework for learning from very few demonstrations of any given task and instantly generalizing to new situations of the same task, without requiring task-specific engineering.
Posted Content
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
TL;DR: FastSpeech 2 is proposed, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by directly training the model with ground-truth target instead of the simplified output from teacher, and introducing more variation information of speech as conditional inputs.
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.
Proceedings Article
Auto-Encoding Variational Bayes
Diederik P. Kingma,Max Welling +1 more
TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.
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
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
Geoffrey E. Hinton,Li Deng,Dong Yu,George E. Dahl,Abdelrahman Mohamed,Navdeep Jaitly,Andrew W. Senior,Vincent Vanhoucke,Patrick Nguyen,Tara N. Sainath,Brian Kingsbury +10 more
TL;DR: This article provides an overview of progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.
Proceedings Article
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization.
TL;DR: Adaptive subgradient methods as discussed by the authors dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradient-based learning, which allows us to find needles in haystacks in the form of very predictive but rarely seen features.