Deep Learning: Methods and Applications

By Li Deng, Dong Yu. 2014

3,839 citations recorded by the source corpus.

This monograph provides an overview of general deep learning methodology and its applications to a variety of signal and information processing tasks. The application areas are chosen with the following three criteria in mind: (1) expertise or knowledge of the authors; (2) the application areas that have already been transformed by the successful use of deep learning technology, such as speech recognition and computer vision; and (3) the application areas that have the potential to be impacted significantly by deep learning and that have been experiencing research growth, including natural language and text processing, information retrieval, and multimodal information processing empowered by multi-task deep learning.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Large Language Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Information Systems

In Large Language Models

Citations in the corpus

MS MARCO: A Human Generated MAchine Reading COmprehension Dataset (2016, background): “Currently, much of the successes of deep learning has been demonstrated in classification tasks [12].”
Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 (2019, background): “As stated in the literature, RNNs are good at predicting the next character in the text, language translation applications, sequential data processing [45, 37].”
Differential Privacy Preservation for Deep Auto-Encoders: an Application of Human Behavior Prediction (2016, background): “In general, deep learning is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text (Deng and Yu 2014).”
Deep learning in neural networks: An overview (2014, background): “5 Deep Hierarchical RL (HRL) and Subgoal Learning with FNNs and RNNs Multiple learnable levels of abstraction (Fu, 1977; Lenat and Brown, 1984; Ring, 1994; Bengio et al., 2013; Deng and Yu, 2014) seem as important for RL as for SL.”
Which Artificial Intelligence Algorithm Better Predicts the Chinese Stock Market? (2018, background): “Previous studies indicate that DL more efﬁciently solves nonlinear problems than traditional methods [19]–[21].”
Neural Networks for Financial Market Risk Classification (2017, background): “All mentioned hyperparameters have been picked up by considering the best practices with empiric origins [2, 4, 9].”
A Deep Learning Approach for Optimization of Systematic Signal Detection in Financial Trading Systems with Big Data (2017, methodology): “With recent advances in hardware and data storage, Big data processing technologies have made it more efficient and affordable to use complex machine learning algorithms in various computational problems [22], [23].”
Geometric Deep Learning: Going beyond Euclidean data (2016, background): “and computer vision [5], [6], [7], [8], [9], [10], [11] (the reader is referred to [12], [13] for many additional examples of successful applications of deep learning).”
DeepSecure: Scalable Provably-Secure Deep Learning (2017, background): “lues to a P-dimensional vector of real values in the range of [0, 1). The final inference for each input sample can be determined by the output unit that has the largest conditional probability value [1]. Figure1demonstratesaschematicdepictionofaCNNmodelconsisting of conventional, pooling, fully-con”
Recurrent Reinforcement Learning: A Hybrid Approach (2015, background): “…deep learning holds the promise of automatically ﬁnding appropriate representations for a given problem, which can be difﬁcult for a human expert, thus avoiding the laborious and challenging step of designing hidden states; see Deng & Yu (2014) for an extensive survey of successful applications.”
Deep learning for computational biology (2016, neutral): “The goal of this review was not to provide comprehensive background on all technical details, which can be found in the more specialized literature (Bengio, 2012; Bengio et al , 2013; Deng, 2014; Schmidhuber, 2015; Goodfellow et al , 2016).”
Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker (2016, background): “Several different network architectures have been proposed, which have enabled to reach state-of-the-art predictive performance in many computer vision and speech recognition tasks (Chen and Lin, 2014; Deng and Yu, 2013).”
Distributed Compressive Sensing: A Deep Learning Approach (2015, background): “Similar to all deep learning methods, it has the important feature of learning the structure of S from the raw data automatically.”
A Survey on Deep Learning in Big Data (2017, background): “Index load time is a challenge now same as space consumption [19].”
Machine learning in acoustics: Theory and applications. (2019, background): “In short, a NN-based ML pipeline is considered DL if it satisﬁes: 73 (i) features are not handcrafted but learned, (ii) features are organized in a hierarchical manner from low-to high-level abstraction, (iii) there are at least two layers of non-linear feature transformations.”
Stochastic Gradient Made Stable: A Manifold Propagation Approach for Large-Scale Optimization (2015, background): “since it is out of the main scope. However, we will explore the distributed variants of the proposed S3GD like [19] in the future. Moreover, extension to non-convex formulations such as deep networks [7] is also a meaningful future direction. 0.0474 0.0518 0.0591 0.0768 m=20 m=50 m=100 m=200 MED11 0”
Past, Present, and Future of Face Recognition: A Review (2020, background): “According to Deng and Yu [98] (2014), three principal reasons for the prominence of deep learning: starting with the drastic growth of processing abilities (e.”