Deep learning—a first meta-survey of selected reviews across scientific disciplines, their commonalities, challenges and research impact

View article
PeerJ Computer Science

Main article text

 

Introduction

Search strategy

Manuscript outline

Fundamental deep learning concepts

Neuron and neural network

Backpropagation and gradient descent

Convolutional neural networks

  • The number of input and output channels;

  • Convolutional kernels defined by their shape.

Fully convolutional neural networks

U-Net

3D U-Net

Deep learning: a survey summary of selected reviews across scientific disciplines

  • computer vision,

  • language processing,

  • medical informatics,

  • and additional works.

Deep learning reviews in computer vision

  • general computer vision,

  • object detection,

  • image segmentation,

  • face recognition,

  • action/motion recognition,

  • biometric recognition,

  • image super-resolution,

  • image captioning,

  • data augmentation,

  • and generative adversarial networks.

General computer vision

Object detection

Image segmentation

Face recognition

Action and motion recognition

Biometric recognition

Image super-resolution

Image captioning

Data augmentation

Generative adversarial networks

Going deeper: common architectures, methods, evaluations, pros, cons, challenges and future directions in computer vision

Deep learning reviews about natural language processing

  • general language processing,

  • language generation and conversation,

  • named entity recognition,

  • sentiment analysis,

  • text summarization,

  • answer selection,

  • word embedding,

  • and financial forecasting.

Natural language processing

Language generation and conversation

Named entity recognition

Sentiment analysis

Text summarization

Answer selection

Word embedding

Financial forecasting

Going deeper: architectures, evaluations, pros, cons, challenges and future directions in language processing

Deep learning reviews in medical informatics

  • health informatics,

  • medical image analysis,

  • medical imaging,

  • health-record analysis,

  • cancer detection and diagnosis,

  • bioinformatics,

  • radiotherapy,

  • pharmacogenomics,

  • and radiology.

Health informatics

Medical image analysis

Medical imaging

Health record analysis

Cancer detection and diagnosis

Bioinformatics

Radiotherapy

Pharmacogenomics

Radiology

Going deeper: architectures, evaluations, pros, cons, challenges and future directions in medical informatics

Additional deep learning reviews

  • big data,

  • reinforcement learning,

  • mobile and wireless networking,

  • mobile multimedia,

  • multimodal learning,

  • remote sensing,

  • graphs,

  • anomaly detection,

  • recommender systems,

  • agriculture,

  • and multiple areas

Big data

Reinforcement learning

Mobile and wireless networking

Mobile multimedia

Multimodal learning

Remote sensing

Graphs

Anomaly detection

Recommender systems

Agriculture

Multiple areas

Going deeper: architectures, evaluations, pros, cons, challenges and future directions in additional works

Conclusion and discussion

  • an overview of current deep learning reviews from various scientific domains;

  • a categorized arrangement of the works according to their data sources, for a domain-specific and historical picture;

  • an extraction of referenced works and citations to show the research influence of deep learning within these domains;

  • the common architectures, methods, pros, cons, evaluations, challenges and future directions for every sub-category;

  • a conclusion and critical discussion of past and future directions for deep learning.

Additional Information and Declarations

Competing Interests

The authors declare that they have no competing interests.

Author Contributions

Jan Egger conceived and designed the experiments, performed the experiments, analyzed the data, prepared figures and/or tables, authored or reviewed drafts of the paper, and approved the final draft.

Antonio Pepe analyzed the data, authored or reviewed drafts of the paper, and approved the final draft.

Christina Gsaxner analyzed the data, authored or reviewed drafts of the paper, and approved the final draft.

Yuan Jin analyzed the data, authored or reviewed drafts of the paper, and approved the final draft.

Jianning Li analyzed the data, authored or reviewed drafts of the paper, and approved the final draft.

Roman Kern analyzed the data, authored or reviewed drafts of the paper, and approved the final draft.

Data Availability

The following information was supplied regarding data availability:

There is no additional data or source code from the authors regarding this survey contribution.

Funding

The authors received funding from the Austrian Science Fund (FWF) KLI 678-B31: ‘enFaced: Virtual and Augmented Reality Training and Navigation Module for 3D-Printed Facial Defect Reconstructions’ and the TU Graz Lead Project (Mechanics, Modeling and Simulation of Aortic Dissection). Moreover, this work was supported by CAMed (COMET K-Project 871132), which is funded by the Austrian Federal Ministry of Transport, Innovation and Technology (BMVIT), and the Austrian Federal Ministry for Digital and Economic Affairs (BMDW), and the Styrian Business Promotion Agency (SFG). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

25 Citations 20,980 Views 683 Downloads

Your institution may have Open Access funds available for qualifying authors. See if you qualify

Publish for free

Comment on Articles or Preprints and we'll waive your author fee
Learn more

Five new journals in Chemistry

Free to publish • Peer-reviewed • From PeerJ
Find out more