What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
Changshui Zhang mostly deals with Artificial intelligence, Pattern recognition, Machine learning, Cluster analysis and Dimensionality reduction.
The concepts of his Artificial intelligence study are interwoven with issues in Graph and Computer vision.
His studies link Data point with Pattern recognition.
His work on Feature selection as part of general Machine learning research is frequently linked to Network traffic simulation, Traffic flow and Data flow diagram, bridging the gap between disciplines.
His Cluster analysis research is multidisciplinary, incorporating perspectives in Matrix decomposition, Theoretical computer science and Data mining.
His Dimensionality reduction study incorporates themes from Embedding, Subspace topology, Linear discriminant analysis and Curse of dimensionality.
His most cited work include:
- Learning Efficient Convolutional Networks through Network Slimming (678 citations)
- Frequency Recognition Based on Canonical Correlation Analysis for SSVEP-Based BCIs (600 citations)
- Label Propagation through Linear Neighborhoods (505 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Pattern recognition, Machine learning, Algorithm and Computer vision.
His work is dedicated to discovering how Artificial intelligence, Data mining are connected with Mixture model and other disciplines.
Changshui Zhang regularly links together related areas like Facial recognition system in his Pattern recognition studies.
His work in Machine learning addresses issues such as Image retrieval, which are connected to fields such as Active learning.
His work on Mathematical optimization expands to the thematically related Algorithm.
His Semi-supervised learning research incorporates themes from Unsupervised learning and Graph.
He most often published in these fields:
- Artificial intelligence (70.45%)
- Pattern recognition (38.18%)
- Machine learning (26.14%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (70.45%)
- Machine learning (26.14%)
- Pattern recognition (38.18%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Machine learning, Pattern recognition, Deep learning and Artificial neural network are his primary areas of study.
His study in Robustness, Adversarial system, Convolutional neural network, MNIST database and Recurrent neural network is done as part of Artificial intelligence.
In his study, which falls under the umbrella issue of Machine learning, Neural coding is strongly linked to Code.
Changshui Zhang focuses mostly in the field of Pattern recognition, narrowing it down to matters related to Image and, in some cases, Interpolation and Degradation.
His research integrates issues of Object and Data mining in his study of Deep learning.
His Artificial neural network research includes themes of Network architecture, Convolution and Pruning.
Between 2017 and 2021, his most popular works were:
- A Deep Neural Framework for Continuous Sign Language Recognition by Iterative Training (56 citations)
- Deep Defense: Training DNNs with Improved Adversarial Robustness (52 citations)
- Sparse DNNs with Improved Adversarial Robustness (50 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His primary areas of investigation include Artificial intelligence, Machine learning, Robustness, Algorithm and Artificial neural network.
His Artificial intelligence study combines topics in areas such as Code and Pattern recognition.
As a part of the same scientific family, Changshui Zhang mostly works in the field of Pattern recognition, focusing on Sequence learning and, on occasion, Recurrent neural network, Gesture recognition, Optical flow and Feature extraction.
His studies deal with areas such as Training set, Linear subspace and Benchmark as well as Machine learning.
His work focuses on many connections between Robustness and other disciplines, such as Adversarial system, that overlap with his field of interest in Computation and Optimization problem.
His Algorithm research is multidisciplinary, relying on both Network architecture, Convolution and Pruning.
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.
