What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Artificial neural network
Artificial intelligence, Artificial neural network, Convolutional neural network, Robotics and Robot kinematics are his primary areas of study.
The Artificial intelligence study combines topics in areas such as Human–computer interaction and Human musculoskeletal system.
His studies deal with areas such as Visualization and Reinforcement learning as well as Artificial neural network.
His Convolutional neural network research incorporates elements of Basis, Approximate inference, Ground truth, Computer vision and Optical flow.
His Ground truth research incorporates themes from Supervised learning, Construct, Frame rate and Feature vector.
His Robotics study incorporates themes from Hand arm and Physical medicine and rehabilitation.
His most cited work include:
- FlowNet: Learning Optical Flow with Convolutional Networks (1644 citations)
- Reach and grasp by people with tetraplegia using a neurally controlled robotic arm (1579 citations)
- FlowNet: Learning Optical Flow with Convolutional Networks (594 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Artificial neural network, Robot, Computer vision and Machine learning.
Artificial intelligence is often connected to Pattern recognition in his work.
His Recurrent neural network study in the realm of Artificial neural network interacts with subjects such as Maxima and minima.
Patrick van der Smagt has researched Robot in several fields, including Simulation and Torque.
His research on Machine learning focuses in particular on Supervised learning.
His research in Convolutional neural network intersects with topics in Ground truth and Image.
He most often published in these fields:
- Artificial intelligence (54.33%)
- Artificial neural network (24.41%)
- Robot (18.11%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial neural network (24.41%)
- Artificial intelligence (54.33%)
- Algorithm (13.39%)
In recent papers he was focusing on the following fields of study:
Patrick van der Smagt mostly deals with Artificial neural network, Artificial intelligence, Algorithm, Function and Quantum.
Patrick van der Smagt works mostly in the field of Artificial neural network, limiting it down to topics relating to Sensitivity and, in certain cases, Feature learning and Deep learning, as a part of the same area of interest.
His biological study spans a wide range of topics, including Machine learning and State space.
In general Machine learning, his work in Structured prediction, MNIST database, Supervised learning and Curse of dimensionality is often linked to Class linking many areas of study.
His Algorithm research includes themes of Smoothing, Inference and Generative model.
His study in Robot is interdisciplinary in nature, drawing from both Probabilistic logic, Divergence, Robotic arm and Adaptation.
Between 2018 and 2021, his most popular works were:
- Layerwise learning for quantum neural networks. (20 citations)
- Bayesian Learning of Neural Network Architectures (9 citations)
- Learning to Fly via Deep Model-Based Reinforcement Learning (8 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Artificial neural network
His scientific interests lie mostly in Artificial neural network, Artificial intelligence, Focus, Algorithm and Function.
Artificial intelligence is closely attributed to State space in his research.
Focus is intertwined with Quantum circuit, Noise, Quantum, Electronic circuit and Computational intelligence in his study.
Patrick van der Smagt frequently studies issues relating to Sampling and Algorithm.
Patrick van der Smagt interconnects Data stream mining and Position in the investigation of issues within Bayesian inference.
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.
