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, Mathematical optimization, Machine learning, Markov decision process and Robot.
Artificial intelligence and Scale are frequently intertwined in his study.
He combines subjects such as Bregman divergence, Non-negative matrix factorization, Motion planning and Projection with his study of Mathematical optimization.
His studies in Machine learning integrate themes in fields like Bayesian Knowledge Tracing and Monte Carlo tree search.
In the subject of general Markov decision process, his work in Partially observable Markov decision process is often linked to Function, thereby combining diverse domains of study.
His research in Robot intersects with topics in Distributed computing, Control engineering, Real-time computing and Fault, Fault model.
His most cited work include:
- A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning (1249 citations)
- Relational learning via collective matrix factorization (866 citations)
- ARA*: Anytime A* with Provable Bounds on Sub-Optimality (451 citations)
What are the main themes of his work throughout his whole career to date?
His main research concerns Artificial intelligence, Machine learning, Mathematical optimization, Theoretical computer science and Markov decision process.
His study in Task extends to Artificial intelligence with its themes.
His Machine learning study incorporates themes from Dynamical systems theory and Inference.
His work carried out in the field of Mathematical optimization brings together such families of science as Robot and Motion planning.
His Theoretical computer science research focuses on subjects like Representation, which are linked to Integer and Predictive state representation.
His work in the fields of Partially observable Markov decision process overlaps with other areas such as Function.
He most often published in these fields:
- Artificial intelligence (47.46%)
- Machine learning (27.68%)
- Mathematical optimization (18.64%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (47.46%)
- Artificial neural network (10.73%)
- Theoretical computer science (16.95%)
In recent papers he was focusing on the following fields of study:
Geoffrey J. Gordon focuses on Artificial intelligence, Artificial neural network, Theoretical computer science, Machine learning and Feature learning.
His Artificial intelligence research incorporates themes from Beam search and Decoding methods.
His Artificial neural network research incorporates elements of Domain adaptation and Mathematical optimization.
His Theoretical computer science study combines topics in areas such as Search algorithm, Graph and Word error rate.
The Machine learning study combines topics in areas such as Adversarial system and Inference.
His Feature learning research integrates issues from Partially observable Markov decision process, Information sensitivity, Function and Representation.
Between 2017 and 2021, his most popular works were:
- Adversarial Multiple Source Domain Adaptation (140 citations)
- On Learning Invariant Representation for Domain Adaptation (101 citations)
- Query-based Workload Forecasting for Self-Driving Database Management Systems (67 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Geoffrey J. Gordon mostly deals with Artificial neural network, Artificial intelligence, Domain adaptation, Invariant and Generalization.
The concepts of his Artificial neural network study are interwoven with issues in Class, Markov decision process and Mathematical optimization, Optimal control.
Geoffrey J. Gordon interconnects Machine learning, Tight binding and Hamiltonian in the investigation of issues within Artificial intelligence.
His work carried out in the field of Machine learning brings together such families of science as Bond length and Graph.
His Domain adaptation research includes elements of Theoretical computer science, Feature learning and Counterexample.
His research integrates issues of Matrix, Rank, Feature vector, Molecule and String in his study of Feature.
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.
