What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Artificial neural network
His scientific interests lie mostly in Artificial intelligence, Transfer of learning, Machine learning, Training set and Semi-supervised learning.
His Transfer of learning research is multidisciplinary, incorporating perspectives in Feature and Pattern recognition.
His Training set study combines topics from a wide range of disciplines, such as Representation and Data mining.
He has researched Semi-supervised learning in several fields, including Manifold, Feature extraction and Generalization error.
Sinno Jialin Pan interconnects Stability, Instance-based learning, Algorithmic learning theory, Cluster analysis and Social web in the investigation of issues within Multi-task learning.
His Feature vector research includes themes of Online machine learning, Unsupervised learning, Computational learning theory and Active learning.
His most cited work include:
- A Survey on Transfer Learning (9736 citations)
- Domain Adaptation via Transfer Component Analysis (1893 citations)
- Cross-domain sentiment classification via spectral feature alignment (549 citations)
What are the main themes of his work throughout his whole career to date?
Sinno Jialin Pan mainly focuses on Artificial intelligence, Machine learning, Transfer of learning, Pattern recognition and Data mining.
His Artificial intelligence study frequently links to other fields, such as Multi-task learning.
The study incorporates disciplines such as Information extraction, Wireless sensor network and Conditional random field in addition to Machine learning.
His Transfer of learning research is multidisciplinary, incorporating elements of Active learning, Feature and Feature vector.
His Semi-supervised learning research incorporates elements of Manifold, Feature extraction and Unsupervised learning, Generalization error.
His work deals with themes such as Algorithm, Regularization and Representation, which intersect with Training set.
He most often published in these fields:
- Artificial intelligence (65.77%)
- Machine learning (38.74%)
- Transfer of learning (27.03%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (65.77%)
- Transfer of learning (27.03%)
- Training set (15.32%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Transfer of learning, Training set, Deep learning and Pattern recognition are his primary areas of study.
His research in Artificial intelligence intersects with topics in Machine learning, Task and Natural language processing.
His Transfer of learning study combines topics in areas such as Systems engineering, Feature, Human–computer interaction and Feature vector.
The concepts of his Feature vector study are interwoven with issues in Feature mapping and Hyperparameter.
His work carried out in the field of Training set brings together such families of science as Algorithm and Regularization.
His Pattern recognition research is multidisciplinary, relying on both Adversarial network and Cross lingual.
Between 2017 and 2021, his most popular works were:
- Domain Generalization with Adversarial Feature Learning (244 citations)
- Sc2Net: Sparse LSTMs for sparse coding ∗ (24 citations)
- Data Poisoning Attacks on Multi-Task Relationship Learning. (20 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Artificial neural network
The scientist’s investigation covers issues in Artificial intelligence, Theoretical computer science, Training set, Quantization and Artificial neural network.
His studies in Artificial intelligence integrate themes in fields like Machine learning and Pattern recognition.
His Machine learning study incorporates themes from Text mining, Learning based, Wireless sensor network and Global Positioning System.
Sinno Jialin Pan works mostly in the field of Theoretical computer science, limiting it down to topics relating to Adversarial system and, in certain cases, Transfer of learning, as a part of the same area of interest.
In most of his Training set studies, his work intersects topics such as Feature.
His research integrates issues of Differentiable function and Computation in his study of Quantization.
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.
