What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Algorithm
- Operating system
His primary scientific interests are in Algorithm, Electronic circuit, Automatic test pattern generation, Electronic engineering and Fault coverage.
His studies in Algorithm integrate themes in fields like Set and Benchmark.
As part of the same scientific family, Kwang-Ting Cheng usually focuses on Electronic circuit, concentrating on Redundancy and intersecting with Logic gate.
His work investigates the relationship between Automatic test pattern generation and topics such as Scan chain that intersect with problems in Boundary scan.
His Fault coverage study also includes
- Stuck-at fault together with Fault model,
- Path delay that connect with fields like Reliability engineering, Real-time computing and Delay calculation.
He combines subjects such as Design for testing and Very-large-scale integration with his study of Test compression.
His most cited work include:
- Fast Human Detection Using a Cascade of Histograms of Oriented Gradients (1265 citations)
- A partial scan method for sequential circuits with feedback (325 citations)
- Automatic Functional Test Generation Using The Extended Finite State Machine Model (250 citations)
What are the main themes of his work throughout his whole career to date?
Kwang-Ting Cheng mainly investigates Algorithm, Electronic engineering, Automatic test pattern generation, Electronic circuit and Artificial intelligence.
His Algorithm study combines topics in areas such as Fault and Set.
His Electronic engineering research includes elements of Transistor and Electrical engineering.
His Automatic test pattern generation research is multidisciplinary, incorporating elements of Theoretical computer science, Boolean satisfiability problem, Computer engineering and Fault coverage.
His work deals with themes such as Redundancy, Very-large-scale integration, Logic gate and Benchmark, which intersect with Electronic circuit.
He interconnects Machine learning, Computer vision and Pattern recognition in the investigation of issues within Artificial intelligence.
He most often published in these fields:
- Algorithm (27.61%)
- Electronic engineering (24.25%)
- Automatic test pattern generation (17.16%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (15.67%)
- Pattern recognition (7.65%)
- Convolutional neural network (3.17%)
In recent papers he was focusing on the following fields of study:
Kwang-Ting Cheng focuses on Artificial intelligence, Pattern recognition, Convolutional neural network, Transistor and Artificial neural network.
His biological study spans a wide range of topics, including Machine learning and Computer vision.
Kwang-Ting Cheng has researched Pattern recognition in several fields, including Overfitting and Sensitivity.
His work in Transistor addresses issues such as Thin-film transistor, which are connected to fields such as Carbon nanotube, Electronic circuit and Semiconductor device modeling.
In his research, Algorithm is intimately related to Block, which falls under the overarching field of Sign function.
As part of one scientific family, Kwang-Ting Cheng deals mainly with the area of Algorithm, narrowing it down to issues related to the Distribution, and often Code.
Between 2017 and 2021, his most popular works were:
- Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm (172 citations)
- Joint Segment-Level and Pixel-Wise Losses for Deep Learning Based Retinal Vessel Segmentation (116 citations)
- MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning (98 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Operating system
- Algorithm
Kwang-Ting Cheng mostly deals with Artificial intelligence, Convolutional neural network, Computer vision, Pattern recognition and Artificial neural network.
Artificial intelligence is frequently linked to Set in his study.
His research integrates issues of Cinematography, Mobile device and Robustness in his study of Computer vision.
His work on Feature extraction as part of general Pattern recognition study is frequently linked to Modalities, therefore connecting diverse disciplines of science.
He usually deals with Convolution and limits it to topics linked to Sign function and Function, Block, Algorithm, Network performance and Initialization.
His Algorithm research incorporates themes from Margin, Distribution, Construct, Generalized function and Sign.
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.
