What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Programming language
- Machine learning
His main research concerns Artificial intelligence, Machine learning, Source code, Conditional random field and Inference.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Variable and Natural language processing.
Charles Sutton combines subjects such as Exploit, Multi-task learning, Optimal control and Topic model with his study of Machine learning.
His Source code research includes themes of Artificial neural network, Attention network, Object and Automatic summarization.
The study incorporates disciplines such as Graphical model, Discriminative model and Data mining in addition to Conditional random field.
In his research, Bayes' theorem and Dynamic topic model is intimately related to Mixture model, which falls under the overarching field of Inference.
His most cited work include:
- An Introduction to Conditional Random Fields for Relational Learning (712 citations)
- Dynamic conditional random fields: factorized probabilistic models for labeling and segmenting sequence data (683 citations)
- An Introduction to Conditional Random Fields (488 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Artificial intelligence, Machine learning, Natural language processing, Inference and Source code.
In Artificial intelligence, Charles Sutton works on issues like Pattern recognition, which are connected to Autoencoder.
His work in Machine learning covers topics such as CRFS which are related to areas like Estimation theory.
His Natural language processing research is multidisciplinary, incorporating elements of Semantics and Word.
His Inference study incorporates themes from Gibbs sampling, Bayesian probability, Markov chain Monte Carlo, Probabilistic logic and Queueing theory.
His Conditional random field study combines topics in areas such as Algorithm and Discriminative model.
He most often published in these fields:
- Artificial intelligence (51.78%)
- Machine learning (24.87%)
- Natural language processing (14.72%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (51.78%)
- Set (11.68%)
- Natural language processing (14.72%)
In recent papers he was focusing on the following fields of study:
Charles Sutton mainly investigates Artificial intelligence, Set, Natural language processing, Program synthesis and Source code.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Java, Machine learning and Code.
His research in Machine learning is mostly concerned with Artificial neural network.
His Set research is multidisciplinary, relying on both Discrete mathematics, Signature and Metadata.
His Natural language processing study incorporates themes from Knowledge base, Matching, Locality, Semantics and Table.
Charles Sutton combines subjects such as Language model, Software development, Embedding, Readability and Structured prediction with his study of Source code.
Between 2018 and 2021, his most popular works were:
- GEMSEC: graph embedding with self clustering (81 citations)
- Big code != big vocabulary: open-vocabulary models for source code (41 citations)
- Global Relational Models of Source Code (36 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Programming language
- Statistics
His scientific interests lie mostly in Artificial intelligence, Source code, Set, Natural language processing and Code.
Charles Sutton has included themes like Machine learning and Pattern recognition in his Artificial intelligence study.
His work in Machine learning addresses subjects such as Graph, which are connected to disciplines such as Software and Abstraction.
Charles Sutton has researched Source code in several fields, including Embedding, Theoretical computer science, Graph Edge and Inductive bias.
His biological study spans a wide range of topics, including Metadata, Matching, Locality, Semantics and Table.
His Natural language processing study combines topics from a wide range of disciplines, such as Software development, Knowledge base and Readability.
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.
