What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His main research concerns Artificial intelligence, Machine learning, Test set, Artificial neural network and Inference.
His biological study spans a wide range of topics, including State, Computer vision and Pattern recognition.
His research integrates issues of Regularization and Convolution in his study of Computer vision.
He is interested in Deep learning, which is a branch of Machine learning.
His Artificial neural network study combines topics from a wide range of disciplines, such as Information extraction and Distributed computing.
His work carried out in the field of Inference brings together such families of science as Probabilistic logic, Data visualization and Dimensionality reduction.
His most cited work include:
- Rethinking the Inception Architecture for Computer Vision (9538 citations)
- Explaining and Harnessing Adversarial Examples (6054 citations)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems (5091 citations)
What are the main themes of his work throughout his whole career to date?
The scientist’s investigation covers issues in Artificial intelligence, Machine learning, Object detection, Contextual image classification and Computer vision.
His Artificial neural network, Deep learning and Test set study in the realm of Artificial intelligence interacts with subjects such as Task.
His research in Test set intersects with topics in Adversarial system and Overfitting.
His Machine learning study combines topics from a wide range of disciplines, such as Focus, Segmentation, Inference and Representation.
He interconnects Computation and Theoretical computer science in the investigation of issues within Inference.
His Computer vision study frequently intersects with other fields, such as Regularization.
He most often published in these fields:
- Artificial intelligence (73.68%)
- Machine learning (35.09%)
- Object detection (20.18%)
What were the highlights of his more recent work (between 2019-2021)?
- Artificial intelligence (73.68%)
- Machine learning (35.09%)
- Object detection (20.18%)
In recent papers he was focusing on the following fields of study:
His primary areas of investigation include Artificial intelligence, Machine learning, Object detection, Point cloud and Test set.
His work in the fields of Artificial intelligence, such as Deep learning, intersects with other areas such as Architecture.
His Machine learning course of study focuses on Segmentation and Leverage.
His work in Object detection addresses issues such as Benchmark, which are connected to fields such as Contrast, Inference and Transfer of learning.
The study incorporates disciplines such as Motion estimation and Lidar in addition to Point cloud.
His Test set research incorporates elements of Semi-supervised learning, Image segmentation, Optical flow, Supervised learning and Discriminative model.
Between 2019 and 2021, his most popular works were:
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset (166 citations)
- Randaugment: Practical automated data augmentation with a reduced search space (131 citations)
- RandAugment: Practical Automated Data Augmentation with a Reduced Search Space (117 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Jonathon Shlens spends much of his time researching Artificial intelligence, Machine learning, Contextual image classification, Object detection and Semi-supervised learning.
His studies deal with areas such as Matching and Generalization as well as Artificial intelligence.
His Generalization research includes elements of Deep learning and Robustness.
His Contextual image classification study incorporates themes from Transformer and Benchmark.
His study brings together the fields of Pattern recognition and Object detection.
Jonathon Shlens works mostly in the field of Semi-supervised learning, limiting it down to concerns involving Segmentation and, occasionally, Test set.
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.
