What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
Marc Peter Deisenroth mostly deals with Artificial intelligence, Machine learning, Reinforcement learning, Gaussian process and Robot.
In the subject of general Artificial intelligence, his work in Robotics, Representation and Feature vector is often linked to Smoothness and Covariance, thereby combining diverse domains of study.
His studies in Robotics integrate themes in fields like Field, Deep learning and Trust region.
His Machine learning research is multidisciplinary, incorporating elements of Robot locomotion, Meta-optimization and Bayesian inference.
His Reinforcement learning study combines topics in areas such as Active learning, Robot learning, Probabilistic logic and State.
His Robot research incorporates themes from Bayesian optimization and Probabilistic-based design optimization.
His most cited work include:
- PILCO: A Model-Based and Data-Efficient Approach to Policy Search (758 citations)
- Deep Reinforcement Learning: A Brief Survey (622 citations)
- A Survey on Policy Search for Robotics (575 citations)
What are the main themes of his work throughout his whole career to date?
Marc Peter Deisenroth mainly focuses on Artificial intelligence, Gaussian process, Machine learning, Reinforcement learning and Algorithm.
His study in the field of Probabilistic logic, Robot and Robotics is also linked to topics like Key.
His Probabilistic logic study incorporates themes from Facial expression and Approximate inference.
His Machine learning research includes themes of Robot learning, Control theory and Robustness.
His biological study spans a wide range of topics, including Active learning, State and Model predictive control.
Marc Peter Deisenroth combines subjects such as Smoothing, Posterior probability, Series and Dynamical system with his study of Algorithm.
He most often published in these fields:
- Artificial intelligence (51.66%)
- Gaussian process (39.74%)
- Machine learning (37.09%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (51.66%)
- Gaussian process (39.74%)
- Machine learning (37.09%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Gaussian process, Machine learning, Scale and Artificial neural network.
His Artificial intelligence study often links to related topics such as Pattern recognition.
His work in the fields of Machine learning, such as Support vector machine, intersects with other areas such as Density estimation.
His Artificial neural network research includes elements of Subspace topology, Dynamical systems theory and Theoretical computer science.
His Robotics research is multidisciplinary, relying on both Latent variable model and Probabilistic logic.
The various areas that Marc Peter Deisenroth examines in his Inference study include Python, Deep learning and Marginal likelihood.
Between 2019 and 2021, his most popular works were:
- Mathematics for Machine Learning (50 citations)
- Efficiently sampling functions from Gaussian process posteriors (21 citations)
- Variational Integrator Networks for Physically Structured Embeddings. (8 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
Marc Peter Deisenroth focuses on Gaussian process, Scale, Curse of dimensionality, Algorithm and Mathematical optimization.
Marc Peter Deisenroth incorporates a variety of subjects into his writings, including Gaussian process, Generalization, Bayesian probability, Deep learning, Inference and Leverage.
His Scale study spans across into subjects like Fraction, Sampling, Sample, Monte Carlo method and Series.
Marc Peter Deisenroth has included themes like Subspace topology, Feature, Bayesian optimization and Feature vector in his Curse of dimensionality study.
His work carried out in the field of Bayesian optimization brings together such families of science as Quantile regression, Optimization problem, Function and Nonlinear system.
His study in Mathematical optimization is interdisciplinary in nature, drawing from both Computational intelligence and Local convergence.
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.
