H-Index & Metrics Top Publications

H-Index & Metrics

Discipline name H-index Citations Publications World Ranking National Ranking
Computer Science H-index 77 Citations 47,111 206 World Ranking 540 National Ranking 325

Research.com Recognitions

Awards & Achievements

2007 - Fellow of the American Association for the Advancement of Science (AAAS)

2002 - ACM Fellow For contributions to machine learning.

1994 - Fellow of the Association for the Advancement of Artificial Intelligence (AAAI) For contributions to the science and practice of machine learning, methodology of machine learning research, and for service to the AI community.

Overview

What is he best known for?

The fields of study he is best known for:

  • Artificial intelligence
  • Machine learning
  • Statistics

His scientific interests lie mostly in Artificial intelligence, Machine learning, Instance-based learning, Generalization and Pattern recognition. His study in Artificial intelligence focuses on Algorithmic learning theory, Reinforcement learning, Overfitting, Boosting and Robustness. His Boosting study integrates concerns from other disciplines, such as BrownBoost, Gradient boosting and Decision tree.

His work in Machine learning addresses issues such as Classifier, which are connected to fields such as Training set. His studies deal with areas such as Object, Inductive transfer, Multi instance multi label and Feature vector as well as Instance-based learning. His work in the fields of Pattern recognition, such as Euclidean distance, intersects with other areas such as Gaussian.

His most cited work include:

  • Ensemble Methods in Machine Learning (4422 citations)
  • Approximate statistical tests for comparing supervised classification learning algorithms (2426 citations)
  • Solving multiclass learning problems via error-correcting output codes (2336 citations)

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

His primary scientific interests are in Artificial intelligence, Machine learning, Reinforcement learning, Pattern recognition and Data mining. His Artificial intelligence research is multidisciplinary, relying on both Computer vision and Natural language processing. Many of his studies on Machine learning apply to Robot learning as well.

His Reinforcement learning research incorporates elements of Mathematical optimization, Bellman equation and State. Thomas G. Dietterich focuses mostly in the field of Mathematical optimization, narrowing it down to topics relating to Markov decision process and, in certain cases, Markov chain. His study in Pattern recognition is interdisciplinary in nature, drawing from both Contextual image classification, Histogram and Cognitive neuroscience of visual object recognition.

He most often published in these fields:

  • Artificial intelligence (60.28%)
  • Machine learning (35.19%)
  • Reinforcement learning (11.50%)

What were the highlights of his more recent work (between 2016-2021)?

  • Artificial intelligence (60.28%)
  • Anomaly detection (7.67%)
  • Machine learning (35.19%)

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

Artificial intelligence, Anomaly detection, Machine learning, Robustness and Markov decision process are his primary areas of study. Artificial neural network and Variety are the subjects of his Artificial intelligence studies. His Anomaly detection research is multidisciplinary, incorporating elements of Deep learning, Anomaly and Outlier.

Much of his study explores Machine learning relationship to Benchmark. His Benchmark study combines topics in areas such as Training set, Baseline and Test set. The concepts of his Markov decision process study are interwoven with issues in Visualization, Monte Carlo method, Mathematical optimization and Reinforcement learning.

Between 2016 and 2021, his most popular works were:

  • Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (285 citations)
  • Deep Anomaly Detection with Outlier Exposure (256 citations)
  • Benchmarking Neural Network Robustness to Common Corruptions and Perturbations (234 citations)

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

  • Artificial intelligence
  • Machine learning
  • Statistics

Artificial intelligence, Robustness, Anomaly detection, Machine learning and Artificial neural network are his primary areas of study. His work is dedicated to discovering how Anomaly detection, Deep learning are connected with Pattern recognition, Outlier, Data modeling, Field and Relation and other disciplines. His work on Test set as part of general Machine learning research is often related to Fraction, thus linking different fields of science.

His work deals with themes such as Variety, Benchmarking, Generative grammar and Data science, which intersect with Artificial neural network. In his research on the topic of Benchmarking, Classifier is strongly related with Residual neural network. Thomas G. Dietterich has included themes like Baseline and Training set in his Benchmark study.

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.

Top Publications

Ensemble Methods in Machine Learning

Thomas G. Dietterich.
multiple classifier systems (2000)

7365 Citations

Solving multiclass learning problems via error-correcting output codes

Thomas G. Dietterich;Ghulum Bakiri.
Journal of Artificial Intelligence Research (1994)

3545 Citations

Approximate statistical tests for comparing supervised classification learning algorithms

Thomas G. Dietterich.
Neural Computation (1998)

3538 Citations

An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization

Thomas G. Dietterich.
Machine Learning (2000)

3119 Citations

Solving the multiple instance problem with axis-parallel rectangles

Thomas G. Dietterich;Richard H. Lathrop;Tomás Lozano-Pérez.
Artificial Intelligence (1997)

2767 Citations

Machine-Learning Research

Thomas G. Dietterich.
Ai Magazine (1997)

1934 Citations

Hierarchical reinforcement learning with the MAXQ value function decomposition

Thomas G. Dietterich.
Journal of Artificial Intelligence Research (2000)

1622 Citations

Adaptive computation and machine learning

Thomas Glen Dietterich.
(1998)

1040 Citations

Learning with many irrelevant features

Hussein Almuallim;Thomas G. Dietterich.
national conference on artificial intelligence (1991)

1037 Citations

Machine Learning for Sequential Data: A Review

Thomas G. Dietterich.
Lecture Notes in Computer Science (2002)

777 Citations

Profile was last updated on December 6th, 2021.
Research.com Ranking is based on data retrieved from the Microsoft Academic Graph (MAG).
The ranking h-index is inferred from publications deemed to belong to the considered discipline.

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

Contact us

Top Scientists Citing Thomas G. Dietterich

Zhi-Hua Zhou

Zhi-Hua Zhou

Nanjing University

Publications: 78

Francisco Herrera

Francisco Herrera

University of Granada

Publications: 69

Sergio Escalera

Sergio Escalera

University of Barcelona

Publications: 69

Petia Radeva

Petia Radeva

University of Barcelona

Publications: 60

Lior Rokach

Lior Rokach

Ben-Gurion University of the Negev

Publications: 53

Jude W. Shavlik

Jude W. Shavlik

University of Wisconsin–Madison

Publications: 44

Huan Liu

Huan Liu

Arizona State University

Publications: 43

Raymond J. Mooney

Raymond J. Mooney

The University of Texas at Austin

Publications: 41

Kristian Kersting

Kristian Kersting

TU Darmstadt

Publications: 39

Qiang Yang

Qiang Yang

Hong Kong University of Science and Technology

Publications: 38

Amit Konar

Amit Konar

Jadavpur University

Publications: 37

André C. P. L. F. de Carvalho

André C. P. L. F. de Carvalho

Universidade de São Paulo

Publications: 37

Alan Fern

Alan Fern

Oregon State University

Publications: 37

Yoshua Bengio

Yoshua Bengio

University of Montreal

Publications: 36

Andrew G. Barto

Andrew G. Barto

University of Massachusetts Amherst

Publications: 36

Something went wrong. Please try again later.