What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Machine learning, Expectation–maximization algorithm and Mathematical optimization.
His Artificial intelligence study frequently involves adjacent topics like Speech recognition.
His Machine learning research is multidisciplinary, relying on both Probabilistic logic and Adaptation.
His biological study spans a wide range of topics, including Simulated annealing, Maxima and minima, Principle of maximum entropy, Estimation theory and Mixture model.
His work deals with themes such as Algorithm and Bayesian inference, which intersect with Mixture model.
The concepts of his Mathematical optimization study are interwoven with issues in Non-negative matrix factorization and Cluster analysis.
His most cited work include:
- Learning systems of concepts with an infinite relational model (491 citations)
- Deterministic annealing EM algorithm (422 citations)
- SMEM Algorithm for Mixture Models (348 citations)
What are the main themes of his work throughout his whole career to date?
Naonori Ueda focuses on Artificial intelligence, Pattern recognition, Machine learning, Algorithm and Artificial neural network.
The study incorporates disciplines such as Computer vision and Expectation–maximization algorithm in addition to Artificial intelligence.
His work in Expectation–maximization algorithm addresses issues such as Mixture model, which are connected to fields such as Maxima and minima.
Naonori Ueda interconnects Bayesian probability and Cluster analysis in the investigation of issues within Pattern recognition.
His Machine learning research is multidisciplinary, incorporating elements of Generative model and Hidden Markov model.
In his work, Relational database is strongly intertwined with Statistical model, which is a subfield of Algorithm.
He most often published in these fields:
- Artificial intelligence (48.60%)
- Pattern recognition (25.70%)
- Machine learning (22.90%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (48.60%)
- Artificial neural network (12.62%)
- Algorithm (17.29%)
In recent papers he was focusing on the following fields of study:
Naonori Ueda mostly deals with Artificial intelligence, Artificial neural network, Algorithm, Pattern recognition and Machine learning.
His Artificial intelligence study combines topics in areas such as Computer vision and Receiver operating characteristic.
His Artificial neural network research incorporates elements of Point process and Series.
His Algorithm research incorporates themes from Decision tree, Function, Upper and lower bounds and Solver.
In general Pattern recognition, his work in Anomaly detection and Convolutional neural network is often linked to Methods statistical and Ground motion linking many areas of study.
His work on Overfitting as part of general Machine learning study is frequently linked to Training, therefore connecting diverse disciplines of science.
Between 2017 and 2021, his most popular works were:
- Land cover classification from fused DSM and UAV images using convolutional neural networks (28 citations)
- Few-shot learning of neural networks from scratch by pseudo example optimization (25 citations)
- Fully Neural Network based Model for General Temporal Point Processes (18 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Naonori Ueda mainly investigates Artificial intelligence, Artificial neural network, Machine learning, Algorithm and Point process.
Naonori Ueda has researched Artificial intelligence in several fields, including Receiver operating characteristic, Topographic Wetness Index, Computer vision and Pattern recognition.
His work on Convolutional neural network as part of general Pattern recognition research is frequently linked to Methods statistical, bridging the gap between disciplines.
The Artificial neural network study combines topics in areas such as Binary classification and Classifier.
His Machine learning study incorporates themes from Estimator and Benchmark.
His work carried out in the field of Algorithm brings together such families of science as Feedforward neural network, Derivative, Exponential growth, Function and Series.
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.
