Journal ArticleDOI
Deep learning
TLDR
Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.Abstract:
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.read more
Citations
More filters
Proceedings ArticleDOI
A neural model for generating natural language summaries of program subroutines
TL;DR: In this article, a neural model that combines words from code with code structure from an AST is presented, which allows the model to learn code structure independent of the text in code.
Journal ArticleDOI
Deep-learning Top Taggers or The End of QCD?
TL;DR: In this article, a convolutional neural network was used to identify top quarks in Monte Carlo simulations of the Standard Model production channel and compared its performance to a multivariate QCD-based top tagger.
Journal ArticleDOI
P Wave Arrival Picking and First-Motion Polarity Determination With Deep Learning
TL;DR: This work trains convolutional neural networks to measure both P-wave arrival times and first-motion polarities, and shows that the classifier picks more polarities overall than the analysts, without sacrificing quality, resulting in almost double the number of focal mechanisms.
Journal ArticleDOI
Towards automatic pulmonary nodule management in lung cancer screening with deep learning
Francesco Ciompi,Kaman Chung,Sarah J. van Riel,Arnaud Arindra Adiyoso Setio,Paul K. Gerke,Colin Jacobs,Ernst T. Scholten,Cornelia Schaefer-Prokop,Mathilde M. W. Wille,Alfonso Marchianò,Ugo Pastorino,Mathias Prokop,Bram van Ginneken +12 more
TL;DR: In this article, a deep learning system based on multi-stream multi-scale convolutional networks was proposed to automatically classify all nodule types relevant for nodule workup, without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule.
Journal ArticleDOI
Survey on computational-intelligence-based UAV path planning
Yijing Zhao,Zheng Zheng,Yang Liu +2 more
TL;DR: An overview of studies on UAV path planning based on CI methods published in major journals and conference proceedings is provided and it is observed that CI methods outperform traditional methods on online and 3D problems.
References
More filters
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal ArticleDOI
Learning representations by back-propagating errors
TL;DR: Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Journal ArticleDOI
Human-level control through deep reinforcement learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Andrei Rusu,Joel Veness,Marc G. Bellemare,Alex Graves,Martin Riedmiller,Andreas K. Fidjeland,Georg Ostrovski,Stig Petersen,Charles Beattie,Amir Sadik,Ioannis Antonoglou,Helen King,Dharshan Kumaran,Daan Wierstra,Shane Legg,Demis Hassabis +18 more
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
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.