What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
Le Song mostly deals with Artificial intelligence, Machine learning, Pattern recognition, Data mining and Theoretical computer science.
All of his Artificial intelligence and Deep learning, Convolutional neural network, Embedding, Graphical model and Kernel method investigations are sub-components of the entire Artificial intelligence study.
Le Song interconnects Event, Parametric statistics and Social network in the investigation of issues within Machine learning.
His Pattern recognition research integrates issues from CURE data clustering algorithm, Fuzzy clustering and Key.
His biological study spans a wide range of topics, including Stochastic process, Transmission, Structure and Cluster analysis.
The Theoretical computer science study combines topics in areas such as Artificial neural network, Decoupling and Graph.
His most cited work include:
- SphereFace: Deep Hypersphere Embedding for Face Recognition (1077 citations)
- A Hilbert space embedding for distributions (580 citations)
- A Kernel Statistical Test of Independence (458 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Algorithm, Machine learning, Mathematical optimization and Theoretical computer science.
Artificial intelligence and Pattern recognition are frequently intertwined in his study.
The various areas that Le Song examines in his Algorithm study include Kernel method, Reproducing kernel Hilbert space, Kernel, Artificial neural network and Embedding.
The study incorporates disciplines such as Nonparametric statistics and Kernel in addition to Kernel.
His work on Recurrent neural network as part of his general Machine learning study is frequently connected to Process, thereby bridging the divide between different branches of science.
His Theoretical computer science study integrates concerns from other disciplines, such as Graph and Graph.
He most often published in these fields:
- Artificial intelligence (39.29%)
- Algorithm (22.92%)
- Machine learning (17.86%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (39.29%)
- Graph (8.33%)
- Theoretical computer science (12.50%)
In recent papers he was focusing on the following fields of study:
Le Song mainly investigates Artificial intelligence, Graph, Theoretical computer science, Artificial neural network and Algorithm.
His Artificial intelligence study frequently involves adjacent topics like Machine learning.
His work carried out in the field of Graph brings together such families of science as Node, Graphical model, Computation and Mathematical optimization.
His Theoretical computer science study combines topics in areas such as Point process, Property, Feature learning and Graph algorithms, Graph.
His Artificial neural network research is multidisciplinary, incorporating elements of Perspective and Bayes' theorem.
Le Song works mostly in the field of Algorithm, limiting it down to topics relating to Feature and, in certain cases, Enhanced Data Rates for GSM Evolution, Embedding, Bridging and Representation.
Between 2019 and 2021, his most popular works were:
- HOPPITY: LEARNING GRAPH TRANSFORMATIONS TO DETECT AND FIX BUGS IN PROGRAMS (38 citations)
- Efficient Probabilistic Logic Reasoning with Graph Neural Networks (15 citations)
- Emerging materials intelligence ecosystems propelled by machine learning (13 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
Le Song spends much of his time researching Artificial intelligence, Graph, Deep learning, Inference and Algorithm.
His multidisciplinary approach integrates Artificial intelligence and Meta learning in his work.
His study explores the link between Graph and topics such as Graph that cross with problems in Attention network, Directed graph, Comprehension, Theoretical computer science and Natural language understanding.
His research integrates issues of Key and Benchmark in his study of Inference.
His Algorithm study combines topics from a wide range of disciplines, such as Parametrization, Hypersphere, Coordinate system and Gradient descent.
His Graph neural networks research incorporates themes from Knowledge graph, Graphical model, Probabilistic logic, Markov chain and JavaScript.
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.
