What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Operating system
Artificial intelligence, Data mining, Machine learning, Information retrieval and Web service are his primary areas of study.
His Artificial intelligence research focuses on subjects like Pattern recognition, which are linked to Computer vision.
The study incorporates disciplines such as Quality, Ranking, Software quality and Web log analysis software in addition to Data mining.
His biological study spans a wide range of topics, including Field and Training set.
In his study, which falls under the umbrella issue of Information retrieval, Constraint and Point of interest is strongly linked to Task.
His research in Web service intersects with topics in Service provider and Mobile QoS.
His most cited work include:
- Recommender systems with social regularization (1135 citations)
- SoRec: social recommendation using probabilistic matrix factorization (992 citations)
- Learning to recommend with social trust ensemble (662 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Machine learning, Data mining, Reliability engineering and World Wide Web.
His study explores the link between Artificial intelligence and topics such as Natural language processing that cross with problems in Conversation.
His studies examine the connections between Data mining and genetics, as well as such issues in Recommender system, with regards to Matrix decomposition and Social network.
His Reliability engineering research includes themes of Software system, Software, Software quality, Software reliability testing and Reliability.
Michael R. Lyu works mostly in the field of World Wide Web, limiting it down to concerns involving Information retrieval and, occasionally, Task and Ranking.
In his work, Quality of service is strongly intertwined with Collaborative filtering, which is a subfield of Web service.
He most often published in these fields:
- Artificial intelligence (30.48%)
- Machine learning (15.09%)
- Data mining (13.93%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (30.48%)
- Natural language processing (4.79%)
- Machine learning (15.09%)
In recent papers he was focusing on the following fields of study:
Michael R. Lyu focuses on Artificial intelligence, Natural language processing, Machine learning, Conversation and Machine translation.
Artificial intelligence and Computer vision are frequently intertwined in his study.
His Natural language processing study combines topics in areas such as Social media, Logical consequence, Word and Code.
His Machine learning study integrates concerns from other disciplines, such as Android app, Android malware, Training set and Mobile malware.
The Conversation study which covers Utterance that intersects with Layer, State, Feature and Feature extraction.
His Machine translation research includes elements of Representation, Subspace topology, Translation and Theoretical computer science.
Between 2018 and 2021, his most popular works were:
- SelFlow: Self-Supervised Learning of Optical Flow (110 citations)
- Tools and benchmarks for automated log parsing (79 citations)
- DDFlow: Learning Optical Flow with Unlabeled Data Distillation (56 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Operating system
- Statistics
Michael R. Lyu mainly investigates Artificial intelligence, Natural language processing, Word, Machine learning and Task.
In most of his Artificial intelligence studies, his work intersects topics such as Field.
His work deals with themes such as Social media, Conversation and Paragraph, which intersect with Natural language processing.
His Word research also works with subjects such as
- Speech recognition that connect with fields like Convolutional neural network, State, Layer and Context,
- Utterance together with Feature extraction.
When carried out as part of a general Machine learning research project, his work on Boosting and Unsupervised learning is frequently linked to work in Transferability and Medical diagnosis, therefore connecting diverse disciplines of study.
His studies deal with areas such as Information retrieval, Reading comprehension, Response generation, Email address and Measure as well as Task.
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.
