What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
His primary areas of study are Supervisory control, Control theory, Discrete system, Artificial intelligence and Discrete event dynamic system.
Within one scientific family, Peter J. Ramadge focuses on topics pertaining to Modular design under Supervisory control, and may sometimes address concerns connected to Predicate, Dynamical systems theory and Automaton.
Peter J. Ramadge focuses mostly in the field of Control theory, narrowing it down to matters related to Bounded function and, in some cases, Zero and Linear system.
In his study, Systems theory and Algorithm is inextricably linked to Theoretical computer science, which falls within the broad field of Discrete system.
His Artificial intelligence study incorporates themes from Neuroscience and Pattern recognition.
His Discrete event dynamic system research incorporates elements of Supervisory control theory, Observability, Nondeterministic algorithm and Formal language.
His most cited work include:
- Supervisory control of a class of discrete event processes (2964 citations)
- The control of discrete event systems (2582 citations)
- Discrete-time multivariable adaptive control (841 citations)
What are the main themes of his work throughout his whole career to date?
Artificial intelligence, Pattern recognition, Control theory, Mathematical optimization and Algorithm are his primary areas of study.
Peter J. Ramadge combines subjects such as Machine learning and Computer vision with his study of Artificial intelligence.
His Pattern recognition research integrates issues from Contextual image classification, Image registration and Voxel.
His work focuses on many connections between Mathematical optimization and other disciplines, such as Bounded function, that overlap with his field of interest in Discrete mathematics and Sequence.
His Algorithm study integrates concerns from other disciplines, such as Matrix decomposition and Multidimensional signal processing.
His Supervisory control research focuses on Formal language and how it connects with Discrete system.
He most often published in these fields:
- Artificial intelligence (44.59%)
- Pattern recognition (23.65%)
- Control theory (16.22%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (44.59%)
- Machine learning (13.51%)
- Mathematical optimization (14.86%)
In recent papers he was focusing on the following fields of study:
Peter J. Ramadge mostly deals with Artificial intelligence, Machine learning, Mathematical optimization, Reinforcement learning and Matrix decomposition.
His Artificial intelligence research focuses on subjects like Pattern recognition, which are linked to Leverage.
His Machine learning study combines topics in areas such as Imitation and K-SVD.
His study in the fields of Iterative method under the domain of Mathematical optimization overlaps with other disciplines such as Divergence.
His work carried out in the field of Reinforcement learning brings together such families of science as Control, Transition, Supervised learning and Constraint.
His biological study deals with issues like Factorization, which deal with fields such as Subspace topology, Applied mathematics, Linear programming and Critical point.
Between 2016 and 2021, his most popular works were:
- Computational approaches to fMRI analysis. (118 citations)
- Screening Tests for Lasso Problems (60 citations)
- A 64-Tile 2.4-Mb In-Memory-Computing CNN Accelerator Employing Charge-Domain Compute (48 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
Peter J. Ramadge spends much of his time researching Artificial intelligence, Bit cell, Binary number, Computational science and Throughput.
His work on Artificial intelligence is being expanded to include thematically relevant topics such as Machine learning.
Among his Bit cell studies, you can observe a synthesis of other disciplines of science such as Convolutional neural network, Multiplication, Charge sharing, Shift register and CMOS.
The concepts of his Binary number study are interwoven with issues in Artificial neural network, Convolution and Deep learning.
In his research, Peter J. Ramadge undertakes multidisciplinary study on Computational science and Clock gating.
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.
