What is he best known for?
The fields of study he is best known for:
- Statistics
- Artificial intelligence
- Machine learning
His scientific interests lie mostly in Inference, Artificial intelligence, Artificial neural network, Algorithm and Divergence.
His work on Inference is being expanded to include thematically relevant topics such as Mathematical optimization.
His Artificial intelligence study combines topics from a wide range of disciplines, such as Machine learning and Forgetting.
His Artificial neural network research includes elements of Probabilistic logic, Discriminative model and Monte Carlo method.
His Algorithm research incorporates elements of Latent variable, Gaussian process, Sampling, Metropolis–Hastings algorithm and Kalman filter.
The study incorporates disciplines such as Key, Approximate inference and Bayesian probability in addition to Gaussian process.
His most cited work include:
- The processing and perception of size information in speech sounds (173 citations)
- Gaussian Process Behaviour in Wide Deep Neural Networks. (166 citations)
- Variational Continual Learning (131 citations)
What are the main themes of his work throughout his whole career to date?
Richard E. Turner focuses on Artificial intelligence, Inference, Machine learning, Algorithm and Gaussian process.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Forgetting and Pattern recognition.
Richard E. Turner has included themes like Artificial neural network, Bayesian neural networks, Divergence, Applied mathematics and Monte Carlo method in his Inference study.
In the subject of general Machine learning, his work in Reinforcement learning, Autoencoder and Feature is often linked to Meta learning and Component, thereby combining diverse domains of study.
His research investigates the connection with Algorithm and areas like Bayesian probability which intersect with concerns in Audiogram and Active learning.
The Gaussian process study combines topics in areas such as Data point, Posterior probability, Approximate inference and Bayesian inference.
He most often published in these fields:
- Artificial intelligence (43.68%)
- Inference (29.31%)
- Machine learning (27.59%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (43.68%)
- Algorithm (24.71%)
- Machine learning (27.59%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Algorithm, Machine learning, Gaussian process and Inference.
His studies in Artificial intelligence integrate themes in fields like Generalization, Missing data and Pattern recognition.
Richard E. Turner has researched Algorithm in several fields, including Marginal likelihood, Calibration, Stochastic process, Bayesian inference and Hidden Markov model.
His work on Autoencoder is typically connected to Meta learning, Set and Component as part of general Machine learning study, connecting several disciplines of science.
His Gaussian process study combines topics in areas such as Separable space, Mathematical analysis, Applied mathematics and Autoregressive model.
His Inference research is multidisciplinary, relying on both Artificial neural network, Monte Carlo method, Prior probability and Dropout.
Between 2019 and 2021, his most popular works were:
- Convolutional Conditional Neural Processes (18 citations)
- Continual Learning with Adaptive Weights (CLAW) (15 citations)
- Continual Deep Learning by Functional Regularisation of Memorable Past (13 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Richard E. Turner mostly deals with Artificial intelligence, Machine learning, Inference, Contextual image classification and Pattern recognition.
His study in the fields of Deep learning under the domain of Artificial intelligence overlaps with other disciplines such as Process.
In his articles, he combines various disciplines, including Machine learning and Component.
As part of his studies on Inference, Richard E. Turner frequently links adjacent subjects like Dropout.
His Contextual image classification research incorporates themes from Artificial neural network, Reduction, Normalization and Convolutional neural network.
The concepts of his Algorithm study are interwoven with issues in Bayesian probability, Monte Carlo method, Approximate inference and Statistical model.
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.
