What is he best known for?
The fields of study he is best known for:
- Programming language
- Operating system
- Artificial intelligence
His primary areas of investigation include Artificial intelligence, Theoretical computer science, Artificial neural network, Abstract interpretation and Scalability.
His work is dedicated to discovering how Artificial intelligence, Machine learning are connected with Data mining and other disciplines.
His Theoretical computer science research integrates issues from Leverage, Conditional random field, Graphical model, Structured prediction and JavaScript.
The various areas that Martin Vechev examines in his Artificial neural network study include Algorithm, Convolutional neural network and Robustness.
He interconnects Static analysis, Inference and Program specification in the investigation of issues within Abstract interpretation.
As a part of the same scientific family, he mostly works in the field of Scalability, focusing on Code and, on occasion, Security analysis and Language model.
His most cited work include:
- AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation (371 citations)
- Code completion with statistical language models (356 citations)
- Securify: Practical Security Analysis of Smart Contracts (270 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Theoretical computer science, Programming language, Artificial intelligence, Artificial neural network and Robustness.
Parallelism is closely connected to Program analysis in his research, which is encompassed under the umbrella topic of Theoretical computer science.
His work in Programming language tackles topics such as Memory model which are related to areas like Overlay and Set.
His Artificial intelligence research focuses on Machine learning and how it relates to JavaScript and Program synthesis.
His work deals with themes such as Scalability and Task, which intersect with Artificial neural network.
His Robustness research is multidisciplinary, incorporating elements of Adversarial system, Algorithm and Network architecture.
He most often published in these fields:
- Theoretical computer science (22.40%)
- Programming language (18.58%)
- Artificial intelligence (15.85%)
What were the highlights of his more recent work (between 2019-2021)?
- Robustness (13.66%)
- Artificial neural network (13.66%)
- Scalability (13.66%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Robustness, Artificial neural network, Scalability, Theoretical computer science and Key.
His study on Robustness is covered under Artificial intelligence.
Martin Vechev works in the field of Artificial intelligence, focusing on Probabilistic logic in particular.
His Scalability study integrates concerns from other disciplines, such as Distributed computing, Leverage, Computer engineering and Range.
Martin Vechev has researched Theoretical computer science in several fields, including Adversarial system, Computational geometry, Approximation algorithm and Inference.
His biological study spans a wide range of topics, including Machine learning and Component.
Between 2019 and 2021, his most popular works were:
- Adversarial Training and Provable Defenses: Bridging the Gap (50 citations)
- VerX: Safety Verification of Smart Contracts (46 citations)
- Silq: a high-level quantum language with safe uncomputation and intuitive semantics (13 citations)
In his most recent research, the most cited papers focused on:
- Programming language
- Operating system
- Artificial intelligence
Robustness, Artificial neural network, Theoretical computer science, Scalability and Distributed computing are his primary areas of study.
His research in Robustness intersects with topics in Smoothing, Rotation, Heuristic, Interpolation and Parameterized complexity.
The concepts of his Artificial neural network study are interwoven with issues in Applied mathematics and Existential quantification.
His Theoretical computer science research incorporates elements of Adversarial system, Representation, Data point, Deep learning and Artificial intelligence.
He combines subjects such as Residual, Computer engineering and Key with his study of Scalability.
Martin Vechev performs multidisciplinary study on Distributed computing and Certification in his works.
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.
