What is he best known for?
The fields of study he is best known for:
- Computer network
- Operating system
- Artificial intelligence
His primary scientific interests are in Distributed computing, Parallel computing, Very-large-scale integration, Computer network and Discrete mathematics.
His Distributed computing study combines topics from a wide range of disciplines, such as Routing table and Isolation.
His Parallel computing research incorporates elements of Systolic array and MISD.
His Very-large-scale integration study incorporates themes from Theoretical computer science, Model of computation, Chip and Binary number, Arithmetic.
His is doing research in Routing protocol, Dynamic Source Routing, Link-state routing protocol, Geographic routing and Wireless Routing Protocol, both of which are found in Computer network.
His study in Discrete mathematics is interdisciplinary in nature, drawing from both Upper and lower bounds, Variety and Multiplication.
His most cited work include:
- GPSR: greedy perimeter stateless routing for wireless networks (6570 citations)
- On optimistic methods for concurrency control (1256 citations)
- On Finding the Maxima of a Set of Vectors (783 citations)
What are the main themes of his work throughout his whole career to date?
Hsiang-Tsung Kung mostly deals with Computer network, Artificial intelligence, Parallel computing, Distributed computing and Algorithm.
His Computer network study combines topics in areas such as Wireless and Wireless network.
The study incorporates disciplines such as Machine learning and Pattern recognition in addition to Artificial intelligence.
His Parallel computing research is multidisciplinary, incorporating perspectives in Systolic array, MISD, Very-large-scale integration and Computation.
His research in Distributed computing focuses on subjects like Dynamic Source Routing, which are connected to Link-state routing protocol.
His research investigates the connection between Algorithm and topics such as Convolutional neural network that intersect with issues in Artificial neural network.
He most often published in these fields:
- Computer network (25.00%)
- Artificial intelligence (16.44%)
- Parallel computing (14.38%)
What were the highlights of his more recent work (between 2012-2021)?
- Artificial intelligence (16.44%)
- Pattern recognition (8.22%)
- Artificial neural network (6.16%)
In recent papers he was focusing on the following fields of study:
Artificial intelligence, Pattern recognition, Artificial neural network, Neural coding and Algorithm are his primary areas of study.
His study focuses on the intersection of Artificial intelligence and fields such as Machine learning with connections in the field of Representation.
His Artificial neural network research includes themes of Distributed computing, Inference, Wireless network, System Fault Tolerance and Cloud computing.
His research in Distributed computing is mostly concerned with Fault tolerance.
His Network packet study is focused on Computer network in general.
His work on Real-time computing expands to the thematically related Computer network.
Between 2012 and 2021, his most popular works were:
- BranchyNet: Fast inference via early exiting from deep neural networks (294 citations)
- Distributed Deep Neural Networks Over the Cloud, the Edge and End Devices (291 citations)
- Detecting Depression using Vocal, Facial and Semantic Communication Cues (71 citations)
In his most recent research, the most cited papers focused on:
- Computer network
- Artificial intelligence
- Operating system
His main research concerns Artificial intelligence, Pattern recognition, Artificial neural network, Neural coding and Inference.
His Artificial intelligence research integrates issues from Machine learning and Natural language processing.
He combines subjects such as Image resolution, Feature and Geolocation with his study of Pattern recognition.
His work deals with themes such as Scalability, Fault tolerance, Distributed computing, Enhanced Data Rates for GSM Evolution and Information privacy, which intersect with Artificial neural network.
His Neural coding study combines topics from a wide range of disciplines, such as Feature, Sparse approximation, Dictionary learning and Discriminative model.
His research in Inference intersects with topics in MNIST database, Systolic array and Feed forward.
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.
