What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Jianxin Wu mainly investigates Artificial intelligence, Pattern recognition, Machine learning, Computer vision and Ensemble learning.
His Artificial intelligence study focuses mostly on Artificial neural network, Face detection, Boosting, Face and Visualization.
His Artificial neural network research integrates issues from Algorithm, Optimization problem, Reduction and Pruning.
His Pattern recognition research is multidisciplinary, relying on both Cognitive neuroscience of visual object recognition and Image.
Jianxin Wu focuses mostly in the field of Machine learning, narrowing it down to matters related to Object detection and, in some cases, Image processing and 3D single-object recognition.
The Ensemble learning study combines topics in areas such as Time delay neural network, Sampling, Undersampling and Class imbalance.
His most cited work include:
- Ensembling neural networks: many could be better than all (1462 citations)
- Exploratory Undersampling for Class-Imbalance Learning (1126 citations)
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression (836 citations)
What are the main themes of his work throughout his whole career to date?
Jianxin Wu spends much of his time researching Artificial intelligence, Pattern recognition, Machine learning, Computer vision and Deep learning.
Artificial intelligence is a component of his Convolutional neural network, Image, Discriminative model, Feature and Contextual image classification studies.
His Pattern recognition research is multidisciplinary, incorporating elements of Object and Histogram.
In the field of Machine learning, his study on Semi-supervised learning and Ensemble learning overlaps with subjects such as Process.
His Ensemble learning research includes themes of Time delay neural network and Artificial neural network.
His work deals with themes such as Convolution, Pruning and Benchmark, which intersect with Deep learning.
He most often published in these fields:
- Artificial intelligence (86.00%)
- Pattern recognition (47.33%)
- Machine learning (31.33%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (86.00%)
- Pattern recognition (47.33%)
- Deep learning (15.33%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Pattern recognition, Deep learning, Machine learning and Convolutional neural network.
All of his Artificial intelligence and Contextual image classification, Discriminative model, Inference, Overfitting and Feature investigations are sub-components of the entire Artificial intelligence study.
His study in Inference is interdisciplinary in nature, drawing from both Artificial neural network and Pruning.
The Pattern recognition research Jianxin Wu does as part of his general Pattern recognition study is frequently linked to other disciplines of science, such as Nature versus nurture, Linear algebra and Rapid expansion, therefore creating a link between diverse domains of science.
Jianxin Wu has researched Deep learning in several fields, including Convolution, Feature learning and Benchmark.
His work in the fields of Machine learning, such as Semi-supervised learning and Feature vector, intersects with other areas such as Metric, Exponential function and DECIPHER.
Between 2018 and 2021, his most popular works were:
- Probabilistic End-To-End Noise Correction for Learning With Noisy Labels (83 citations)
- ThiNet: Pruning CNN Filters for a Thinner Net (75 citations)
- AutoPruner: An end-to-end trainable filter pruning method for efficient deep model inference (46 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Computer vision
Jianxin Wu focuses on Artificial intelligence, Deep learning, Pattern recognition, Algorithm and End-to-end principle.
His biological study spans a wide range of topics, including Machine learning and Data science.
His Deep learning research incorporates elements of Image and Image retrieval.
Jianxin Wu combines subjects such as Object detection and Robustness with his study of Pattern recognition.
His Algorithm study also includes
- Pooling and related Channel, Code, Inference and Kernel,
- Pruning which intersects with area such as Optimization problem, Convolutional neural network, Artificial neural network and Segmentation,
- Convolution that connect with fields like Support vector machine and Kernel.
His research in End-to-end principle intersects with topics in Probabilistic logic, Overfitting and Categorization.
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.
