What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
Tommi S. Jaakkola mainly focuses on Algorithm, Artificial intelligence, Mathematical optimization, Machine learning and Linear programming relaxation.
His research integrates issues of Spline, Theoretical computer science, Cluster analysis and Reinforcement learning in his study of Algorithm.
The Artificial intelligence study combines topics in areas such as Margin, Natural language processing and Pattern recognition.
Tommi S. Jaakkola combines subjects such as Markov decision process, State, Variational message passing and Applied mathematics with his study of Mathematical optimization.
His Machine learning research includes themes of Variable-order Bayesian network and Data mining.
His Linear programming relaxation research incorporates themes from Graphical model, Inference and Coordinate descent.
His most cited work include:
- An introduction to variational methods for graphical models (3107 citations)
- Exploiting Generative Models in Discriminative Classifiers (1210 citations)
- Maximum-Margin Matrix Factorization (918 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Algorithm, Machine learning, Theoretical computer science and Inference are his primary areas of study.
His Artificial intelligence research integrates issues from Natural language processing, Task and Pattern recognition.
His Algorithm course of study focuses on Graphical model and Mathematical optimization.
His study explores the link between Machine learning and topics such as Data mining that cross with problems in Cluster analysis.
His research investigates the connection between Theoretical computer science and topics such as Graph that intersect with problems in Graph.
His research links Bayesian network with Inference.
He most often published in these fields:
- Artificial intelligence (34.94%)
- Algorithm (21.15%)
- Machine learning (19.55%)
What were the highlights of his more recent work (between 2018-2021)?
- Theoretical computer science (17.31%)
- Artificial intelligence (34.94%)
- Machine learning (19.55%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Theoretical computer science, Artificial intelligence, Machine learning, Graph and Algorithm.
Tommi S. Jaakkola has researched Theoretical computer science in several fields, including Decision tree, Equivalence, Representation and Constant function.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Simple, Encoder and Pattern recognition.
His Machine learning research is multidisciplinary, incorporating perspectives in Variation and Inference.
His Graph study combines topics from a wide range of disciplines, such as Artificial neural network, Recurrent neural network, Graph, Generative grammar and Convolutional neural network.
His research in Algorithm intersects with topics in Linear approximation and Relaxation.
Between 2018 and 2021, his most popular works were:
- A Deep Learning Approach to Antibiotic Discovery (253 citations)
- A graph-convolutional neural network model for the prediction of chemical reactivity. (159 citations)
- Analyzing Learned Molecular Representations for Property Prediction. (138 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
The scientist’s investigation covers issues in Theoretical computer science, Artificial intelligence, Graph, Machine learning and Generative grammar.
His Theoretical computer science research incorporates elements of Autoregressive model and Drug discovery.
His Artificial intelligence research is multidisciplinary, incorporating elements of Workflow, Complement and Natural language processing.
His work on Convolutional neural network is typically connected to Patent literature, Rationalization and Counterfactual thinking as part of general Machine learning study, connecting several disciplines of science.
His Convolutional neural network study combines topics in areas such as Artificial neural network and Computer graphics.
His work on Generative model as part of general Generative grammar research is often related to Novelty and Vocabulary, thus linking different fields of science.
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.
