What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
Kumar Chellapilla spends much of his time researching Artificial intelligence, Mathematical proof, Machine learning, Evolutionary programming and Genetic programming.
He works mostly in the field of Artificial intelligence, limiting it down to topics relating to The Internet and, in certain cases, Pattern recognition.
His Evolutionary programming research focuses on Algorithm and how it relates to Reverse engineering, Bitmap and Image warping.
His Genetic programming research incorporates themes from Programming language and Genetic algorithm, Mathematical optimization.
As a member of one scientific family, Kumar Chellapilla mostly works in the field of Mathematical optimization, focusing on Crossover and, on occasion, Theoretical computer science.
His work deals with themes such as Evolutionary algorithm, Contrast and Outcome, which intersect with Artificial neural network.
His most cited work include:
- High Performance Convolutional Neural Networks for Document Processing (325 citations)
- Using Machine Learning to Break Visual Human Interaction Proofs (HIPs) (222 citations)
- Combining mutation operators in evolutionary programming (217 citations)
What are the main themes of his work throughout his whole career to date?
Kumar Chellapilla mainly focuses on Artificial intelligence, Evolutionary programming, Algorithm, Evolutionary computation and Evolutionary algorithm.
Kumar Chellapilla interconnects Machine learning, Speech recognition and Pattern recognition in the investigation of issues within Artificial intelligence.
His research in Evolutionary programming focuses on subjects like Genetic representation, which are connected to Java Evolutionary Computation Toolkit.
His work in the fields of Bloom filter and Optimization problem overlaps with other areas such as Binary form.
Within one scientific family, Kumar Chellapilla focuses on topics pertaining to Genetic algorithm under Evolutionary algorithm, and may sometimes address concerns connected to Genetic programming and Crossover.
In Segmentation, Kumar Chellapilla works on issues like Convolutional neural network, which are connected to Speedup.
He most often published in these fields:
- Artificial intelligence (31.37%)
- Evolutionary programming (18.63%)
- Algorithm (16.67%)
What were the highlights of his more recent work (between 2008-2012)?
- Theoretical computer science (9.80%)
- Classifier (6.86%)
- Voltage graph (3.92%)
In recent papers he was focusing on the following fields of study:
His main research concerns Theoretical computer science, Classifier, Voltage graph, Artificial intelligence and Algorithm.
His Theoretical computer science research includes themes of Trie, Scalability and Graph, Graph compression.
His work carried out in the field of Classifier brings together such families of science as Data mining, Malware analysis and Top-down and bottom-up design.
His Artificial intelligence research incorporates elements of Web search query, Search engine, Machine learning and Behavioral pattern.
His studies deal with areas such as Anomaly detection and Web traffic as well as Web search query.
His study looks at the relationship between Algorithm and topics such as Block graph, which overlap with Outerplanar graph, Comparability graph and Butterfly graph.
Between 2008 and 2012, his most popular works were:
- Finding Dense Subgraphs with Size Bounds (162 citations)
- Bottom-up analysis of network sites (45 citations)
- WebCop: locating neighborhoods of malware on the web (40 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
Kumar Chellapilla focuses on Computer security, Suspect, Top-down and bottom-up design, Classifier and Malware analysis.
His Computer security study incorporates themes from Web page, World Wide Web, The Internet and Web crawler.
Kumar Chellapilla incorporates Suspect and Data mining in his studies.
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.
