What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
James T. Kwok mainly focuses on Artificial intelligence, Pattern recognition, Support vector machine, Machine learning and Kernel method.
His Artificial intelligence study typically links adjacent topics like Computer vision.
In the subject of general Pattern recognition, his work in Feature extraction, Wavelet transform and Feature vector is often linked to Domain, thereby combining diverse domains of study.
His study looks at the relationship between Support vector machine and fields such as Quadratic programming, as well as how they intersect with chemical problems.
The concepts of his Machine learning study are interwoven with issues in Class and Categorization.
James T. Kwok works mostly in the field of Kernel method, limiting it down to topics relating to Algorithm and, in certain cases, Mathematical optimization, Theoretical computer science and Rate of convergence, as a part of the same area of interest.
His most cited work include:
- Domain Adaptation via Transfer Component Analysis (1893 citations)
- Core Vector Machines: Fast SVM Training on Very Large Data Sets (792 citations)
- Transfer learning via dimensionality reduction (457 citations)
What are the main themes of his work throughout his whole career to date?
James T. Kwok spends much of his time researching Artificial intelligence, Pattern recognition, Algorithm, Machine learning and Mathematical optimization.
His Artificial intelligence study often links to related topics such as Data mining.
James T. Kwok studied Algorithm and Matrix that intersect with Singular value decomposition.
His work on Semi-supervised learning as part of general Machine learning research is frequently linked to Space, thereby connecting diverse disciplines of science.
His Mathematical optimization research incorporates elements of Time complexity, Regularization and Convex function.
His work on Radial basis function kernel as part of general Kernel method study is frequently linked to Gaussian function, bridging the gap between disciplines.
He most often published in these fields:
- Artificial intelligence (53.87%)
- Pattern recognition (32.04%)
- Algorithm (23.59%)
What were the highlights of his more recent work (between 2015-2021)?
- Artificial intelligence (53.87%)
- Algorithm (23.59%)
- Mathematical optimization (20.07%)
In recent papers he was focusing on the following fields of study:
James T. Kwok mostly deals with Artificial intelligence, Algorithm, Mathematical optimization, Machine learning and Matrix.
His Artificial intelligence study combines topics in areas such as Sample and Pattern recognition.
His Algorithm research incorporates themes from Rate of convergence and Matrix norm.
His Mathematical optimization study integrates concerns from other disciplines, such as Convex function and Stochastic gradient descent.
James T. Kwok combines subjects such as Bayesian probability and Taxonomy with his study of Machine learning.
His biological study spans a wide range of topics, including Regularization, Convolution, Frequency domain and Neural coding.
Between 2015 and 2021, his most popular works were:
- Generalizing from a Few Examples: A Survey on Few-shot Learning (197 citations)
- Multi-Label Learning with Global and Local Label Correlation (79 citations)
- Loss-aware Binarization of Deep Networks (78 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of study are Artificial intelligence, Algorithm, Machine learning, Mathematical optimization and Matrix.
His studies in Artificial intelligence integrate themes in fields like Matrix decomposition and Optimization problem.
His work carried out in the field of Algorithm brings together such families of science as Matrix norm and Matrix completion.
His Machine learning study incorporates themes from Categorization and Taxonomy.
The Mathematical optimization study combines topics in areas such as Stochastic gradient descent and Variance reduction.
His Matrix research is multidisciplinary, incorporating elements of Regularization and Key.
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.
