H-Index & Metrics Best Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science D-index 99 Citations 150,352 395 World Ranking 147 National Ranking 8

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Artificial neural network

Jürgen Schmidhuber focuses on Artificial intelligence, Artificial neural network, Recurrent neural network, Speech recognition and Machine learning. His research brings together the fields of Pattern recognition and Artificial intelligence. The study incorporates disciplines such as Contextual image classification, Feature, Computer vision and Benchmark in addition to Artificial neural network.

Jürgen Schmidhuber combines subjects such as Language model, Sequence learning, Algorithm, State and Hidden Markov model with his study of Recurrent neural network. While the research belongs to areas of Speech recognition, Jürgen Schmidhuber spends his time largely on the problem of Handwriting recognition, intersecting his research to questions surrounding Robustness. His study on Deep learning and Supervised learning is often connected to Focus as part of broader study in Machine learning.

His most cited work include:

  • Long short-term memory (35520 citations)
  • Deep learning in neural networks (8339 citations)
  • Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks (2529 citations)

What are the main themes of his work throughout his whole career to date?

His primary scientific interests are in Artificial intelligence, Artificial neural network, Machine learning, Reinforcement learning and Recurrent neural network. His studies deal with areas such as Curiosity, Computer vision and Pattern recognition as well as Artificial intelligence. His Artificial neural network research includes themes of Algorithm, Deep learning, Convolutional neural network and Benchmark.

He studies Machine learning, namely Unsupervised learning. His Reinforcement learning research is multidisciplinary, relying on both Mathematical optimization and Neuroevolution. His research integrates issues of Time delay neural network and Speech recognition, Hidden Markov model in his study of Recurrent neural network.

He most often published in these fields:

  • Artificial intelligence (67.88%)
  • Artificial neural network (28.49%)
  • Machine learning (21.23%)

What were the highlights of his more recent work (between 2015-2021)?

  • Artificial intelligence (67.88%)
  • Artificial neural network (28.49%)
  • Machine learning (21.23%)

In recent papers he was focusing on the following fields of study:

Jürgen Schmidhuber spends much of his time researching Artificial intelligence, Artificial neural network, Machine learning, Reinforcement learning and Recurrent neural network. Artificial intelligence is closely attributed to Pattern recognition in his research. His Artificial neural network study combines topics from a wide range of disciplines, such as Minification, Speech recognition, Set, Minimax and Differentiable function.

His Machine learning study integrates concerns from other disciplines, such as Perception, Principle of compositionality, Contextual image classification, Modular design and Variety. Jürgen Schmidhuber has included themes like Hindsight bias, State, Supervised learning, Sample and Robot in his Reinforcement learning study. His Recurrent neural network study combines topics in areas such as Feature, Feed forward, Histogram, Nonlinear system and Perplexity.

Between 2015 and 2021, his most popular works were:

  • LSTM: A Search Space Odyssey (2223 citations)
  • A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots (434 citations)
  • Recurrent World Models Facilitate Policy Evolution (241 citations)

In his most recent research, the most cited papers focused on:

  • Artificial intelligence
  • Machine learning
  • Statistics

Jürgen Schmidhuber mainly focuses on Artificial intelligence, Recurrent neural network, Artificial neural network, Machine learning and Reinforcement learning. The Artificial intelligence study combines topics in areas such as State and Perception. His Recurrent neural network research is multidisciplinary, incorporating perspectives in Language model, Speech recognition, Entropy, Treebank and Entropy.

His Artificial neural network research is multidisciplinary, incorporating elements of Segmentation, Pattern recognition, Set, Inference and Minimax. His studies in Machine learning integrate themes in fields like Structure, Generator and Natural language. His biological study spans a wide range of topics, including Hallucinating, Humanoid robot, iCub, Set and Sample.

This overview was generated by a machine learning system which analysed the scientist’s body of work. If you have any feedback, you can contact us here.

Best Publications

Long short-term memory

Sepp Hochreiter;Jürgen Schmidhuber.
Neural Computation (1997)

37080 Citations

Deep learning in neural networks

Jürgen Schmidhuber.
Neural Networks (2015)

13236 Citations

Multi-column deep neural networks for image classification

Dan Cireşan;Ueli Meier;Juergen Schmidhuber.
computer vision and pattern recognition (2012)

3348 Citations

LSTM: A Search Space Odyssey

Klaus Greff;Rupesh K. Srivastava;Jan Koutnik;Bas R. Steunebrink.
IEEE Transactions on Neural Networks (2017)

2589 Citations

Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks

Alex Graves;Santiago Fernández;Faustino Gomez;Jürgen Schmidhuber.
international conference on machine learning (2006)

2449 Citations

Framewise phoneme classification with bidirectional LSTM and other neural network architectures

Alex Graves;Jürgen Schmidhuber.
international joint conference on neural network (2005)

1976 Citations

A Novel Connectionist System for Unconstrained Handwriting Recognition

A. Graves;M. Liwicki;S. Fernandez;R. Bertolami.
IEEE Transactions on Pattern Analysis and Machine Intelligence (2009)

1601 Citations

Learning to Forget: Continual Prediction with LSTM

Felix A. Gers;Jürgen A. Schmidhuber;Fred A. Cummins.
Neural Computation (2000)

1469 Citations

2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures

Alex Graves;Jürgen Schmidhuber.
Neural Networks (2005)

1397 Citations

Highway Networks

Rupesh Kumar Srivastava;Klaus Greff;Jürgen Schmidhuber.
(2015)

1305 Citations

If you think any of the details on this page are incorrect, let us know.

Contact us

Best Scientists Citing Jürgen Schmidhuber

Yoshua Bengio

Yoshua Bengio

University of Montreal

Publications: 191

Björn Schuller

Björn Schuller

Imperial College London

Publications: 150

Sergey Levine

Sergey Levine

University of California, Berkeley

Publications: 91

Kyunghyun Cho

Kyunghyun Cho

New York University

Publications: 89

Julian Togelius

Julian Togelius

New York University

Publications: 81

Hermann Ney

Hermann Ney

RWTH Aachen University

Publications: 81

Pierre-Yves Oudeyer

Pierre-Yves Oudeyer

French Institute for Research in Computer Science and Automation - INRIA

Publications: 71

U. Rajendra Acharya

U. Rajendra Acharya

Ngee Ann Polytechnic

Publications: 68

Klaus-Robert Müller

Klaus-Robert Müller

Technical University of Berlin

Publications: 66

Marcus Hutter

Marcus Hutter

Australian National University

Publications: 66

Shinji Watanabe

Shinji Watanabe

Carnegie Mellon University

Publications: 64

Trevor Darrell

Trevor Darrell

University of California, Berkeley

Publications: 63

Pieter Abbeel

Pieter Abbeel

University of California, Berkeley

Publications: 63

Aaron Courville

Aaron Courville

University of Montreal

Publications: 60

Lianwen Jin

Lianwen Jin

South China University of Technology

Publications: 59

Philip S. Yu

Philip S. Yu

University of Illinois at Chicago

Publications: 59

Something went wrong. Please try again later.