What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Programming language
His primary scientific interests are in Artificial intelligence, Machine learning, Markov decision process, Data mining and Probabilistic logic.
His study ties his expertise on Pattern recognition together with the subject of Artificial intelligence.
His Machine learning research is multidisciplinary, relying on both Bayesian probability, Heuristics, Heuristic and Hindsight bias.
His Markov decision process research integrates issues from Domain, Control and Mixture model.
His research in the fields of Anomaly detection overlaps with other disciplines such as Anomaly.
In his study, Language bias and Key is strongly linked to Mathematical optimization, which falls under the umbrella field of Probabilistic logic.
His most cited work include:
- FF-Replan: a baseline for probabilistic planning (216 citations)
- Multi-task reinforcement learning: a hierarchical Bayesian approach (202 citations)
- UCT for tactical assault planning in real-time strategy games (144 citations)
What are the main themes of his work throughout his whole career to date?
His scientific interests lie mostly in Artificial intelligence, Machine learning, Reinforcement learning, Mathematical optimization and Data mining.
Alan Fern focuses mostly in the field of Artificial intelligence, narrowing it down to topics relating to Heuristics and, in certain cases, Heuristic.
His research integrates issues of Beam search and Bayesian probability in his study of Machine learning.
The various areas that Alan Fern examines in his Reinforcement learning study include Robot, Human–computer interaction, Adaptation and Control.
In his work, Domain is strongly intertwined with Task, which is a subfield of Human–computer interaction.
Alan Fern works mostly in the field of Mathematical optimization, limiting it down to topics relating to Markov decision process and, in certain cases, Theoretical computer science, as a part of the same area of interest.
He most often published in these fields:
- Artificial intelligence (50.43%)
- Machine learning (32.61%)
- Reinforcement learning (19.13%)
What were the highlights of his more recent work (between 2015-2021)?
- Artificial intelligence (50.43%)
- Reinforcement learning (19.13%)
- Machine learning (32.61%)
In recent papers he was focusing on the following fields of study:
The scientist’s investigation covers issues in Artificial intelligence, Reinforcement learning, Machine learning, Data mining and Anomaly detection.
His work carried out in the field of Artificial intelligence brings together such families of science as Key and Natural language processing.
His study in Reinforcement learning is interdisciplinary in nature, drawing from both Robot, Cognitive psychology, Control and Human–computer interaction.
His Machine learning research includes themes of Tree and Algorithm design.
His study focuses on the intersection of Data mining and fields such as Process with connections in the field of Wireless sensor network and Convolution.
His research in Anomaly detection tackles topics such as Detector which are related to areas like Supervised learning, Identification and Probably approximately correct learning.
Between 2015 and 2021, his most popular works were:
- Visualizing and Understanding Atari Agents. (81 citations)
- Incorporating Expert Feedback into Active Anomaly Discovery (67 citations)
- Fast Online Trajectory Optimization for the Bipedal Robot Cassie (37 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Programming language
His main research concerns Artificial intelligence, Reinforcement learning, Machine learning, Anomaly detection and Data mining.
In general Artificial intelligence study, his work on Benchmark, Feature extraction and Recurrent neural network often relates to the realm of Bottleneck and Work, thereby connecting several areas of interest.
His Benchmark research is multidisciplinary, incorporating perspectives in Training set, Baseline and Test set.
His Recurrent neural network research includes elements of Range, Interpretability and Representation.
The study incorporates disciplines such as Focus and Human–computer interaction in addition to Reinforcement learning.
His Anomaly detection study integrates concerns from other disciplines, such as Tree, Ranking and False positive paradox.
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.
