What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
Artificial intelligence, Computer vision, Image segmentation, Segmentation and Pattern recognition are his primary areas of study.
Many of his studies involve connections with topics such as Machine learning and Artificial intelligence.
His Computer vision study combines topics from a wide range of disciplines, such as Pipeline and Computer graphics.
His work deals with themes such as Thresholding, Submodular set function, Mathematical optimization, Heuristic and Markov chain, which intersect with Image segmentation.
His Segmentation study incorporates themes from Image processing, Computational complexity theory, Algorithm and Image fusion.
Pushmeet Kohli has researched Pattern recognition in several fields, including Stereopsis, Curvature and Set.
His most cited work include:
- Indoor segmentation and support inference from RGBD images (2739 citations)
- KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera (1650 citations)
- Relational inductive biases, deep learning, and graph networks (891 citations)
What are the main themes of his work throughout his whole career to date?
His scientific interests lie mostly in Artificial intelligence, Computer vision, Machine learning, Algorithm and Artificial neural network.
His study connects Pattern recognition and Artificial intelligence.
Pushmeet Kohli interconnects Process and Computer graphics in the investigation of issues within Computer vision.
His Machine learning study integrates concerns from other disciplines, such as Inference and Data mining.
His Artificial neural network study also includes
- Robustness that connect with fields like Adversarial system,
- Theoretical computer science which intersects with area such as Set.
His Image segmentation research includes themes of Mathematical optimization and Random field.
He most often published in these fields:
- Artificial intelligence (61.64%)
- Computer vision (23.53%)
- Machine learning (17.39%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (61.64%)
- Artificial neural network (14.07%)
- Algorithm (14.58%)
In recent papers he was focusing on the following fields of study:
Pushmeet Kohli mostly deals with Artificial intelligence, Artificial neural network, Algorithm, Robustness and Reinforcement learning.
His primary area of study in Artificial intelligence is in the field of Deep learning.
He has included themes like Inductive bias, Formal verification, Theoretical computer science, Optimization problem and Computation in his Artificial neural network study.
His work on Linear programming as part of general Algorithm study is frequently connected to Invariant, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them.
His Robustness research is multidisciplinary, relying on both Adversarial system, Bounded function, Invariant and Obfuscation.
His studies deal with areas such as Range and Set as well as Reinforcement learning.
Between 2017 and 2021, his most popular works were:
- Relational inductive biases, deep learning, and graph networks (891 citations)
- Improved protein structure prediction using potentials from deep learning (518 citations)
- On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models (189 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Pushmeet Kohli mainly investigates Artificial intelligence, Artificial neural network, Robustness, Machine learning and Algorithm.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Domain, Structure and Natural language processing.
His Artificial neural network study combines topics in areas such as Optimization problem, Upper and lower bounds and Deep learning.
His research investigates the connection with Deep learning and areas like Gradient descent which intersect with concerns in Segmentation.
The concepts of his Robustness study are interwoven with issues in Adversarial system and Norm.
His research investigates the connection between Machine learning and topics such as Key that intersect with issues in Labeled data, Constant and Invariant.
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.
