Keith M. Chugg

What is he best known for?

The fields of study he is best known for:

• Algorithm
• Telecommunications
• Statistics

His main research concerns Algorithm, Convolutional code, Communication channel, Concatenated error correction code and Electronic engineering. His Algorithm study combines topics from a wide range of disciplines, such as Graph theory, Combinatorics and Channel state information. The Convolutional code study combines topics in areas such as Bit stuffing, Least number bits and Encoding.

His Communication channel research is multidisciplinary, incorporating perspectives in Estimation theory, Recursion, Matched filter, Sequence and Transient response. As a part of the same scientific study, Keith M. Chugg usually deals with the Concatenated error correction code, concentrating on Linear code and frequently concerns with Low-density parity-check code. He interconnects Co-channel interference, Frequency offset and Communications system in the investigation of issues within Electronic engineering.

His most cited work include:

• Method and apparatus for communications using turbo like codes (170 citations)
• Method and apparatus for communications using improved turbo like codes (127 citations)
• MLSE for an unknown channel .I. Optimality considerations (106 citations)

What are the main themes of his work throughout his whole career to date?

His primary areas of investigation include Algorithm, Electronic engineering, Communication channel, Decoding methods and Concatenated error correction code. Keith M. Chugg focuses mostly in the field of Algorithm, narrowing it down to matters related to Theoretical computer science and, in some cases, Graphical model and Metric. His work deals with themes such as Transmitter, Signal, Communications system and Fading, which intersect with Electronic engineering.

His Communication channel research includes elements of Maximum likelihood, Sequence and Estimator. His studies in Decoding methods integrate themes in fields like Coding, Control theory and Equalization. His Concatenated error correction code study integrates concerns from other disciplines, such as Sequential decoding, Low-density parity-check code and Linear code.

He most often published in these fields:

• Algorithm (43.64%)
• Electronic engineering (23.64%)
• Communication channel (23.64%)

What were the highlights of his more recent work (between 2015-2021)?

• Artificial neural network (8.48%)
• Artificial intelligence (9.70%)
• Inference (6.67%)

In recent papers he was focusing on the following fields of study:

Keith M. Chugg spends much of his time researching Artificial neural network, Artificial intelligence, Inference, Convolutional neural network and Machine learning. His Artificial neural network research includes themes of Network performance and Computation. His Artificial intelligence research incorporates elements of Sampling and CMOS.

His research integrates issues of Computational complexity theory, Field-programmable gate array and Computer engineering in his study of Inference. His Convolutional neural network research incorporates themes from Energy consumption, Kernel and Hyperparameter. With his scientific publications, his incorporates both Logarithm and Algorithm.

Between 2015 and 2021, his most popular works were:

• Accelerating Training of Deep Neural Networks via Sparse Edge Processing (17 citations)
• Pre-Defined Sparse Neural Networks With Hardware Acceleration (13 citations)
• High-rate WiFi broadcasting in crowded scenarios via lightweight coordination of multiple access points (13 citations)

In his most recent research, the most cited papers focused on:

• Algorithm
• Telecommunications
• Statistics

His primary scientific interests are in Artificial neural network, Inference, Artificial intelligence, Computer engineering and Convolutional neural network. His Artificial neural network study which covers Network performance that intersects with Computation and Function. As part of the same scientific family, Keith M. Chugg usually focuses on Inference, concentrating on Field-programmable gate array and intersecting with Reconfigurability, Computer architecture, Computational complexity theory and Applications of artificial intelligence.

His study looks at the relationship between Artificial intelligence and fields such as Pattern recognition, as well as how they intersect with chemical problems. His work carried out in the field of Computer engineering brings together such families of science as Speedup and Flexibility. His research investigates the connection between Convolutional neural network and topics such as Kernel that intersect with issues in Parsing, FLOPS, Algorithm and Hyperparameter.