What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
His scientific interests lie mostly in Artificial intelligence, Machine learning, Inference, Pattern recognition and Theoretical computer science.
He combines subjects such as Algorithm and Invariant with his study of Artificial intelligence.
His biological study spans a wide range of topics, including Sampling, Differentiable function, Bayes' theorem and Fourier series.
The concepts of his Inference study are interwoven with issues in Latent variable, Convergence, Bayesian inference, Mathematical optimization and Gibbs sampling.
The Mixture model research Max Welling does as part of his general Pattern recognition study is frequently linked to other disciplines of science, such as Filter, therefore creating a link between diverse domains of science.
His work deals with themes such as Dynamical systems theory, Graph, Complex dynamics, Unsupervised learning and Graph, which intersect with Theoretical computer science.
His most cited work include:
- Auto-Encoding Variational Bayes (7123 citations)
- Auto-Encoding Variational Bayes (3799 citations)
- Semi-Supervised Classification with Graph Convolutional Networks (3436 citations)
What are the main themes of his work throughout his whole career to date?
Max Welling spends much of his time researching Artificial intelligence, Algorithm, Inference, Machine learning and Artificial neural network.
His Artificial intelligence research includes elements of Invariant and Pattern recognition.
His Invariant research is multidisciplinary, relying on both MNIST database and Autoencoder.
Max Welling has researched Algorithm in several fields, including Sampling, Probabilistic logic, Bayesian probability, Bayes' theorem and Monte Carlo method.
He has included themes like Theoretical computer science, Latent variable, Markov chain Monte Carlo, Bayesian inference and Gibbs sampling in his Inference study.
His research combines Graph and Theoretical computer science.
He most often published in these fields:
- Artificial intelligence (44.19%)
- Algorithm (29.61%)
- Inference (26.20%)
What were the highlights of his more recent work (between 2019-2021)?
- Algorithm (29.61%)
- Artificial intelligence (44.19%)
- Artificial neural network (17.08%)
In recent papers he was focusing on the following fields of study:
Max Welling focuses on Algorithm, Artificial intelligence, Artificial neural network, Equivariant map and Theoretical computer science.
His Algorithm research incorporates themes from Probabilistic logic, Inference, Robustness and Markov chain Monte Carlo.
His work carried out in the field of Artificial intelligence brings together such families of science as Machine learning and Pattern recognition.
His research investigates the link between Artificial neural network and topics such as Regularization that cross with problems in Training set.
Max Welling interconnects Message passing, Transformer, Homogeneous space, Graph and Function in the investigation of issues within Equivariant map.
His Theoretical computer science research is multidisciplinary, incorporating perspectives in Mcmc algorithm, User verification, Code and Reinforcement learning.
Between 2019 and 2021, his most popular works were:
- Contrastive Learning of Structured World Models (46 citations)
- SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks (15 citations)
- Plannable Approximations to MDP Homomorphisms: Equivariance under Actions (14 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Quantum mechanics
His main research concerns Equivariant map, Theoretical computer science, Algorithm, Artificial neural network and Feature learning.
His Equivariant map study incorporates themes from Graph and Graph.
His work on Causal graph as part of general Theoretical computer science research is often related to Causal relations, thus linking different fields of science.
His research in Algorithm tackles topics such as Transformer which are related to areas like Robustness and Corollary.
Feature learning is a subfield of Artificial intelligence that he studies.
His Autoencoder, Latent variable, Embedding and Principal component analysis study in the realm of Artificial intelligence interacts with subjects such as Meta learning.
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.
