What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Artificial neural network
Yu Cheng spends much of his time researching Artificial intelligence, Artificial neural network, Machine learning, Benchmark and Pattern recognition.
Yu Cheng integrates Artificial intelligence and Code in his research.
His Artificial neural network research incorporates elements of Circulant matrix, Fast Fourier transform and Time complexity.
Many of his research projects under Machine learning are closely connected to Network architecture, Original data and Domain adaptation with Network architecture, Original data and Domain adaptation, tying the diverse disciplines of science together.
The various areas that Yu Cheng examines in his Benchmark study include Anomaly detection, Data mining, Autoencoder and Kernel.
His study in the fields of Segmentation under the domain of Pattern recognition overlaps with other disciplines such as Sequence modeling.
His most cited work include:
- A Survey of Model Compression and Acceleration for Deep Neural Networks (397 citations)
- Deep Model Based Domain Adaptation for Fault Diagnosis (252 citations)
- MMD GAN: Towards Deeper Understanding of Moment Matching Network (210 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Machine learning, Natural language processing, Pattern recognition and Computer vision.
His work in Deep learning, Language model, Artificial neural network, Feature and Question answering are all subfields of Artificial intelligence research.
His Artificial neural network research incorporates themes from Circulant matrix, Algorithm, Theoretical computer science and Convolutional neural network.
In general Machine learning, his work in Leverage is often linked to Metric linking many areas of study.
His work in Natural language processing addresses subjects such as Representation, which are connected to disciplines such as Matching.
His Pattern recognition study which covers Facial recognition system that intersects with Feature extraction.
He most often published in these fields:
- Artificial intelligence (74.88%)
- Machine learning (26.11%)
- Natural language processing (17.73%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (74.88%)
- Natural language processing (17.73%)
- Question answering (10.34%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Natural language processing, Question answering, Language model and Machine learning.
His research brings together the fields of Computer vision and Artificial intelligence.
Yu Cheng has included themes like Relation and Coreference in his Natural language processing study.
His studies in Question answering integrate themes in fields like Theoretical computer science, Feature learning and Closed captioning.
His biological study spans a wide range of topics, including Compression, Transformer and Benchmark.
Yu Cheng combines subjects such as Subspace topology and Robustness with his study of Machine learning.
Between 2019 and 2021, his most popular works were:
- UNITER: UNiversal Image-TExt Representation Learning (69 citations)
- Discourse-Aware Neural Extractive Text Summarization (39 citations)
- Large-Scale Adversarial Training for Vision-and-Language Representation Learning (34 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
Artificial intelligence, Question answering, Language model, Natural language processing and Inference are his primary areas of study.
His Artificial intelligence course of study focuses on Machine learning and Benchmark.
Yu Cheng interconnects Matching and Sentence in the investigation of issues within Question answering.
The Matching study combines topics in areas such as Theoretical computer science, Artificial neural network, Interpretability, Graph and Machine translation.
His research investigates the connection between Language model and topics such as Transformer that intersect with problems in Speech recognition, HERO and Closed captioning.
His Natural language processing research focuses on Coreference and how it relates to Relation.
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.
