Match!

Deep learning

Published on May 28, 2015in Nature43.07
· DOI :10.1038/nature14539
Yann LeCun92
Estimated H-index: 92
(NYU: New York University),
Yoshua Bengio121
Estimated H-index: 121
(UdeM: Université de Montréal),
Geoffrey E. Hinton123
Estimated H-index: 123
(U of T: University of Toronto)
Cite
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.
  • References (32)
  • Citations (6840)
Cite
References32
Newest
Published on Feb 23, 2015in Journal of Chemical Information and Modeling3.97
Junshui Ma10
Estimated H-index: 10
,
Robert P. Sheridan33
Estimated H-index: 33
+ 2 AuthorsVladimir Svetnik12
Estimated H-index: 12
Neural networks were widely used for quantitative structure–activity relationships (QSAR) in the 1990s. Because of various practical issues (e.g., slow on large problems, difficult to train, prone to overfitting, etc.), they were superseded by more robust methods like support vector machine (SVM) and random forest (RF), which arose in the early 2000s. The last 10 years has witnessed a revival of neural networks in the machine learning community thanks to new methods for preventing overfitting, m...
Published on Feb 1, 2015in Nature43.07
Volodymyr Mnih29
Estimated H-index: 29
,
Koray Kavukcuoglu45
Estimated H-index: 45
+ 16 AuthorsGeorg Ostrovski8
Estimated H-index: 8
An artificial agent is developed that learns to play a diverse range of classic Atari 2600 computer games directly from sensory experience, achieving a performance comparable to that of an expert human player; this work paves the way to building general-purpose learning algorithms that bridge the divide between perception and action.
Published on Jan 9, 2015in Science41.04
Hui Yuan Xiong8
Estimated H-index: 8
(CIFAR: Canadian Institute for Advanced Research),
Babak Alipanahi17
Estimated H-index: 17
(CIFAR: Canadian Institute for Advanced Research)
+ 14 AuthorsTimothy R. Hughes72
Estimated H-index: 72
(CIFAR: Canadian Institute for Advanced Research)
To facilitate precision medicine and whole genome annotation, we developed a machine learning technique that scores how strongly genetic variants affect RNA splicing, whose alteration contributes to many diseases. Analysis of over 650,000 intronic and exonic variants reveals widespread patterns of mutation-driven aberrant splicing. Intronic disease mutations alter splicing nine times more often than common variants, and missense exonic disease mutations that least impact protein function are fiv...
Published on Dec 18, 2014in PLOS Computational Biology
Charles F. Cadieu16
Estimated H-index: 16
(McGovern Institute for Brain Research),
Ha Hong8
Estimated H-index: 8
(MIT: Massachusetts Institute of Technology)
+ 5 AuthorsJames J. DiCarlo38
Estimated H-index: 38
(McGovern Institute for Brain Research)
The primate visual system achieves remarkable visual object recognition performance even in brief presentations, and under changes to object exemplar, geometric transformations, and background variation (a.k.a. core visual object recognition). This remarkable performance is mediated by the representation formed in inferior temporal (IT) cortex. In parallel, recent advances in machine learning have led to ever higher performing models of object recognition using artificial deep neural networks (D...
Published on Jun 15, 2014in Bioinformatics4.53
Michael K. K. Leung15
Estimated H-index: 15
(U of T: University of Toronto),
Hui Yuan Xiong8
Estimated H-index: 8
(U of T: University of Toronto)
+ 1 AuthorsBrendan J. Frey57
Estimated H-index: 57
(U of T: University of Toronto)
Motivation: Alternative splicing (AS) is a regulated process that directs the generation of different transcripts from single genes. A computational model that can accurately predict splicing patterns based on genomic features and cellular context is highly desirable, both in understanding this widespread phenomenon, and in exploring the effects of genetic variations on AS. Methods: Using a deep neural network, we developed a model inferred from mouse RNA-Seq data that can predict splicing patte...
Marc'Aurelio Ranzato37
Estimated H-index: 37
(U of T: University of Toronto),
Volodymyr Mnih29
Estimated H-index: 29
(U of T: University of Toronto)
+ 1 AuthorsGeoffrey E. Hinton123
Estimated H-index: 123
(U of T: University of Toronto)
This paper describes a Markov Random Field for real-valued image modeling that has two sets of latent variables. One set is used to gate the interactions between all pairs of pixels, while the second set determines the mean intensities of each pixel. This is a powerful model with a conditional distribution over the input that is Gaussian, with both mean and covariance determined by the configuration of latent variables, which is unlike previous models that were restricted to using Gaussians with...
Clément Farabet15
Estimated H-index: 15
(NYU: New York University),
Camille Couprie15
Estimated H-index: 15
(NYU: New York University)
+ 1 AuthorsYann LeCun92
Estimated H-index: 92
(NYU: New York University)
Scene labeling consists of labeling each pixel in an image with the category of the object it belongs to. We propose a method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes centered on each pixel. The method alleviates the need for engineered features, and produces a powerful representation that captures texture, shape, and contextual information. We report results using multiple postprocessing methods t...
Published on Aug 1, 2013in Nature43.07
Moritz Helmstaedter32
Estimated H-index: 32
(MPG: Max Planck Society),
Kevin L. Briggman24
Estimated H-index: 24
(MPG: Max Planck Society)
+ 3 AuthorsWinfried Denk70
Estimated H-index: 70
(MPG: Max Planck Society)
Improved electron microscopy methods are used to map a mammalian retinal circuit of close to 1,000 neurons; the work reveals a new type of retinal bipolar neuron and suggests functional mechanisms for known visual computations.
Published on Nov 1, 2012in IEEE Signal Processing Magazine7.60
Geoffrey E. Hinton123
Estimated H-index: 123
(U of T: University of Toronto),
Li Deng72
Estimated H-index: 72
(Microsoft)
+ 8 AuthorsTara N. Sainath31
Estimated H-index: 31
Most current speech recognition systems use hidden Markov models (HMMs) to deal with the temporal variability of speech and Gaussian mixture models (GMMs) to determine how well each state of each HMM fits a frame or a short window of frames of coefficients that represents the acoustic input. An alternative way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural n...
Published on Aug 1, 2012in Neural Networks5.79
Dan C. Ciresan17
Estimated H-index: 17
(Dalle Molle Institute for Artificial Intelligence Research),
Ueli Meier19
Estimated H-index: 19
(Dalle Molle Institute for Artificial Intelligence Research)
+ 1 AuthorsJuergen Schmidhuber70
Estimated H-index: 70
(Dalle Molle Institute for Artificial Intelligence Research)
We describe the approach that won the final phase of the German traffic sign recognition benchmark. Our method is the only one that achieved a better-than-human recognition rate of 99.46%. We use a fast, fully parameterizable GPU implementation of a Deep Neural Network (DNN) that does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. Combining various DNNs trained on differently preprocessed data into a Multi-Column DNN (MCDNN) further boos...
Cited By6840
Newest
Zhenguo Nie (CMU: Carnegie Mellon University), Haoliang Jiang1
Estimated H-index: 1
(CMU: Carnegie Mellon University),
Levent Burak Kara19
Estimated H-index: 19
(CMU: Carnegie Mellon University)
Published on 2019in Expert Systems With Applications4.29
Kai Lei7
Estimated H-index: 7
(PKU: Peking University),
Bing Zhang1
Estimated H-index: 1
(PKU: Peking University)
+ 2 AuthorsYing Shen3
Estimated H-index: 3
(PKU: Peking University)
Abstract Algorithmic trading is a continuous perception and decision making problem, where environment perception requires to learn feature representation from highly nonstationary and noisy financial time series, and decision making requires the algorithm to explore the environment and simultaneously make correct decisions in an online manner without any supervised information. To address these two problems, we propose a time-driven feature-aware jointly deep reinforcement learning model (TFJ-D...
Published on Feb 1, 2020in Expert Systems With Applications4.29
Rama Syamala Sreepada1
Estimated H-index: 1
(NITR: National Institute of Technology, Rourkela),
Bidyut Kr. Patra6
Estimated H-index: 6
(NITR: National Institute of Technology, Rourkela)
Abstract Recommender system has been established as an effective tool for users in providing personalized suggestions in many domains, especially in e-commerce. In these domains, recommendations are provided based on the feedback (ratings) given by the users. However, recommendations provided by the traditional approaches are biased towards the popular items (items that receive more number of ratings). As a result, unpopular items are left out and these items remain un-recommended and unsold. Th...
Published on Feb 1, 2020in Optics and Lasers in Engineering4.06
Lina Zhou (PolyU: Hong Kong Polytechnic University), Yin Xiao (PolyU: Hong Kong Polytechnic University), Wen Chen24
Estimated H-index: 24
(PolyU: Hong Kong Polytechnic University)
Abstract In this paper, we experimentally demonstrate for the first time to our knowledge that optical encryption based on diffractive imaging is vulnerable to the attacks using learning methods. Using machine learning attack, an opponent is capable to retrieve unknown plaintexts from the given ciphertexts. The proposed method adopts end-to-end learning to extract a superior mapping relationship between the ciphertexts and the plaintexts. Without a direct retrieval or estimate of optical encrypt...
Published on Jan 1, 2020in Talanta4.92
Qiannan Duan (NU: Nanjing University), Yuan Hu (NU: Nanjing University)+ 4 AuthorsZhaoyi Xu (NU: Nanjing University)
Abstract Analysis on mixture toxicity (Mix-tox) of the multi-chemical space is constantly followed with interest for many researchers. Conventional toxicity tests with time-consuming and costly operations make researchers can only establish some toxicity prediction models aiming to a limited sampling dimension. The rapid development of machine learning (ML) algorithm will accelerate the exploration of many fields involving toxicity analysis. Rather than the model calculation capacity, the challe...
Published on 2020in Information Sciences5.52
Yun Zhang16
Estimated H-index: 16
(CAS: Chinese Academy of Sciences),
Sam Kwong43
Estimated H-index: 43
(CityU: City University of Hong Kong),
Shiqi Wang20
Estimated H-index: 20
(CityU: City University of Hong Kong)
Abstract Video data has become the largest source of data consumed globally. Due to the rapid growth of video applications and boosting demands for higher quality video services, video data volume has been increasing explosively worldwide, which has been the most severe challenge for multimedia computing, transmission and storage. Video coding by compressing videos into a much smaller size is one of the key solutions; however, its development has become saturated to some extent while the compres...
Published on 2020in Future Generation Computer Systems5.77
Wenbin Jiang7
Estimated H-index: 7
(HUST: Huazhong University of Science and Technology),
Yangsong Zhang (HUST: Huazhong University of Science and Technology)+ 4 AuthorsHai Jin47
Estimated H-index: 47
(HUST: Huazhong University of Science and Technology)
Abstract D e e p n e u r a l n e t w o r k s (DNNs) have become more and more important for big data analysis. They usually use data parallelism or model parallelism for extreme scale computing. However, the two approaches realize the performance improvement mainly by using coarse-grained parallelization schemes. Neither can fully exploit the potentials of the parallelism of many-core systems (such as GPUs) for neural network models. Here, a new f i n e − g r a i n e d p a r a l l e l i s m s t ...