What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
Thomas L. Griffiths spends much of his time researching Artificial intelligence, Natural language processing, Bayesian inference, Inference and Probabilistic logic.
His Artificial intelligence research includes elements of Probability distribution and Machine learning.
His Natural language processing study combines topics in areas such as Segmentation, Text segmentation, Language acquisition, Statistical model and Semantics.
His Bayesian inference research incorporates elements of Concept learning, Generalization, Cognitive science and Approximate inference.
His study in Inference is interdisciplinary in nature, drawing from both Causality, Class, Simple and L-attributed grammar, Stochastic context-free grammar.
His Probabilistic logic study also includes
- Cognitive psychology most often made with reference to Cognition,
- Context-free grammar and Maximum likelihood most often made with reference to Hybrid Monte Carlo.
His most cited work include:
- Finding scientific topics (4035 citations)
- The author-topic model for authors and documents (1237 citations)
- Probabilistic Topic Models (945 citations)
What are the main themes of his work throughout his whole career to date?
Thomas L. Griffiths mainly focuses on Artificial intelligence, Machine learning, Bayesian inference, Cognitive psychology and Cognition.
His research links Natural language processing with Artificial intelligence.
The concepts of his Natural language processing study are interwoven with issues in Language acquisition and Word.
His work in Machine learning addresses issues such as Set, which are connected to fields such as Structure.
His research in Bayesian inference intersects with topics in Concept learning, Generalization, Prior probability and Posterior probability.
His research on Cognition frequently connects to adjacent areas such as Cognitive science.
He most often published in these fields:
- Artificial intelligence (48.60%)
- Machine learning (19.93%)
- Bayesian inference (19.93%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (48.60%)
- Machine learning (19.93%)
- Cognition (14.15%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Machine learning, Cognition, Cognitive psychology and Structure.
His Artificial intelligence research is multidisciplinary, relying on both Cognitive model and Natural language processing.
His research integrates issues of Range, Meta learning, Bayes' theorem and Set in his study of Machine learning.
The study incorporates disciplines such as Control and Cognitive science in addition to Cognition.
His Cognitive psychology research incorporates themes from Test and Social psychology.
His work deals with themes such as Representation and Plan, which intersect with Structure.
Between 2017 and 2021, his most popular works were:
- Recasting Gradient-Based Meta-Learning as Hierarchical Bayes (117 citations)
- Recasting gradient-based meta-learning as hierarchical bayes (91 citations)
- Resource-rational analysis: Understanding human cognition as the optimal use of limited computational resources. (85 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
His scientific interests lie mostly in Artificial intelligence, Machine learning, Cognition, Cognitive model and Set.
He usually deals with Artificial intelligence and limits it to topics linked to Psychological research and Deep neural networks.
His work carried out in the field of Machine learning brings together such families of science as Prior probability, Meta learning and Bayes' theorem.
His Cognition research is multidisciplinary, incorporating perspectives in Cognitive psychology, Cognitive science and Natural language processing.
His Natural language processing study integrates concerns from other disciplines, such as Big data, Image, Categorical variable and Markov chain Monte Carlo.
His studies deal with areas such as Robot, Plan, Human–computer interaction and Action as well as Set.
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.
