Science Explorer Back to mapMap
Discussion
Topic · Artificial Intelligence

Neural Networks and Reservoir Computing

Neural Networks and Reservoir Computing is a research topic within Artificial Intelligence. Science Explorer counts 18k research works in it since 1955. 9.9% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the application of photonic reservoir computing for neural computation, machine learning, and information processing. It explores the use of semiconductor lasers, neuromorphic photonics, and optical neural networks, as well as the implementation of echo state networks and nonlinear dynamics in photonic systems.

  • Photonic Reservoir Computing
  • Neuromorphic Photonics
  • Optical Neural Networks
  • Machine Learning
  • Semiconductor Lasers
  • Echo State Networks
  • Nonlinear Dynamics
  • Optoelectronic Reservoir Computing
  • Diffractive Optical Neural Networks
  • Neural Network Training
Research works
18k
fractional, since 1955
In the world top 10%
1.8k
per year above
Top-10% rate
9.9%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+99%
the tick is no change
Largest producer
China
41% of the 10 largest, 2022-now
Neural Networks and Reservoir Computing

Which countries lead Neural Networks and Reservoir Computing research?

By volume, China and the United States publish the most (2.7k and 1.4k works in 2022-now).

By volume, 2022-now

  1. 1 China 2.7k works
  2. 2 United States 1.4k works
  3. 3 Japan 462 works
  4. 4 India 417 works
  5. 5 Germany 359 works
  6. 6 United Kingdom 294 works
  7. 7 South Korea 264 works
  8. 8 Italy 246 works
  9. 9 France 213 works
  10. 10 Canada 180 works

How concentrated that is

The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.

China: 41.1%United States: 21.8%Japan: 7.0%India: 6.4%6 others listed: 23.7%41%largest
China2,698 · 41.1%United States1,431 · 21.8%Japan462 · 7.0%India417 · 6.4%6 others listed1,556 · 23.7%

Shares of the rows listed above, not of the whole node.

Which institutions lead Neural Networks and Reservoir Computing research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Neural Networks and Reservoir Computing research, followed by Centre National de la Recherche Scientifique and Beijing University of Posts and Telecommunications.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 170 works
  2. 2 Centre National de la Recherche ScientifiqueFrance 90 works
  3. 3 Beijing University of Posts and TelecommunicationsChina 73 works
  4. 4 Tsinghua UniversityChina 70 works
  5. 5 The University of TokyoJapan 69 works
  6. 6 Zhejiang UniversityChina 68 works
  7. 7 Shanghai Jiao Tong UniversityChina 63 works
  8. 8 University of Electronic Science and Technology of ChinaChina 61 works
  9. 9 Huazhong University of Science and TechnologyChina 54 works
  10. 10 Peking UniversityChina 46 works

Who are the leading researchers in Neural Networks and Reservoir Computing?

The most-cited researchers publishing on Neural Networks and Reservoir Computing include Zhong Lin Wang, Yoshua Bengio and Geoffrey E. Hinton.

  1. 1 Zhong Lin Wang United States 491k citations
  2. 2 Yoshua Bengio Canada 476k citations
  3. 3 Geoffrey E. Hinton Canada 454k citations
  4. 4 Valery L. Feigin New Zealand 341k citations
  5. 5 Yury G. Gogotsi United States 313k citations
  6. 6 Karl John Friston United Kingdom 310k citations
  7. 7 Wei Huang China 267k citations
  8. 8 Yann LeCun United States 256k citations
  9. 9 Kenji Watanabe Japan 237k citations
  10. 10 Takashi Taniguchi Japan 227k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

What are the most cited papers in Neural Networks and Reservoir Computing?

The most cited paper in Neural Networks and Reservoir Computing is "A scheme for efficient quantum computation with linear optics" (E. Knill, Raymond Laflamme, Gerard J Milburn, 2001), with 5,952 citations. Next come "A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures" (5,666) and "Deep Sparse Rectifier Neural Networks" (5,420).

Most cited papers
#PaperReleasedCitations
1 A scheme for efficient quantum computation with linear optics E. Knill, Raymond Laflamme, Gerard J Milburn · Nature 2001 5,952
2 A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures Yong Yu, Xiaosheng Si, Changhua Hu et al. · Neural Computation 21 May 2019 5,666
3 Deep Sparse Rectifier Neural Networks Xavier Glorot, Antoine Bordes, Yoshua Bengio 11 Apr 2011 5,420
4 Quantum machine learning Jacob Biamonte, Péter Wittek, Nicola Pancotti et al. · Nature Open access Sep 2017 4,771
5 A variational eigenvalue solver on a photonic quantum processor Alberto Peruzzo, Jarrod R. McClean, Peter Shadbolt et al. · Nature Communications Open access 23 Jul 2014 4,756
All 99 most cited papers, with filters and sorting

Where is Neural Networks and Reservoir Computing research done?

The largest centres of Neural Networks and Reservoir Computing research in 2022-now are Beijing (China), Shanghai (China), Tokyo (Japan) and Nanjing (China). Among places with at least 20 works in it, it is an unusually large share of all research in Palma and Eindhoven.

Largest cities, 2022-now

  1. 1 BeijingChina 558 works
  2. 2 ShanghaiChina 251 works
  3. 3 TokyoJapan 196 works
  4. 4 NanjingChina 161 works
  5. 5 SeoulSouth Korea 140 works
  6. 6 HangzhouChina 138 works
  7. 7 ChengduChina 122 works
  8. 8 WuhanChina 122 works
  9. 9 Xi'anChina 116 works
  10. 10 GuangzhouChina 100 works

Where it is the local speciality

  1. PalmaES · 21.5 works14×
  2. EindhovenNL · 30.0 works8.5×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Neural Networks and Reservoir Computing than the world average.

See Neural Networks and Reservoir Computing on the map

Where is the best place to study Neural Networks and Reservoir Computing?

Among universities, judged by research, Dongguk University, National University of Singapore and Tsinghua University score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%20%40%mean 17.18%fractional works in this field (log) →share of work in the world top 10% →Dongguk UniversityNational University …Tsinghua UniversityZhejiang University
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1Dongguk UniversitySouth Korea 71.135.7%11.7×15 +902.2%
2National University of SingaporeSingapore 68.524.0%4.3×35 +200.3%
3Tsinghua UniversityChina 64.415.1%4.4×70 +214.9%
4Zhejiang UniversityChina 62.513.4%3.7×68 +265.4%
5University of California, Los AngelesUnited States 60.518.1%4.5×36 +82.2%
6Peking UniversityChina 59.016.0%3.2×46 +74.9%
7Shanghai Jiao Tong UniversityChina 58.912.1%3.2×63 +113.7%
8The University of TokyoJapan 58.75.7%8.0×69 +51.7%
9Shenzhen UniversityChina 57.622.6%3.8×19 +36.3%
10University of Electronic Science and Technology of ChinaChina 57.49.1%7.9×61 +164.9%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Neural Networks and Reservoir Computing, country by country

Is Neural Networks and Reservoir Computing research growing?

Output in 2022-2025 was 99% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Neural Networks and Reservoir Computing.

still counting19801990200020102020
grewheldshrank

The same series as a ribbon: one cell per year, darker for more. The line above answers how much; this answers when.

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Neural Networks and Reservoir Computing as a percentage of every work published that year, 0.029% in 2024.

still counting0.020%0.040%Neural Networks and Reservoir Computing0.037% in 202519801990200020102020

Fractional works of Neural Networks and Reservoir Computing over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Neural Networks and Reservoir Computing9.8% in 2025200020102020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

Which topics inside it are moving

Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.

Discussion

Ask a question or share a note about Neural Networks and Reservoir Computing. Posts are plain text and can be reported.