Education
Brief Bio
Dr. Pyeatt earned his B.S. and M.S. degrees at Texas Tech University and then worked in industry, designing microprocessor-based control and data-acquisition systems and applying neural networks at Texaco, work that resulted in a U.S. patent. He earned his doctorate in Computer Science, focusing on artificial intelligence, from Colorado State University in 1999. He spent 13 years on the faculty of Texas Tech University, including three years as Department Chair of Computer Science at Texas Tech University at Abilene, before joining the South Dakota School of Mines and Technology in 2012.
His research joins machine learning with computer architecture. With the Stanford School of Medicine he developed the reinforcement-learning methodology behind a closed-loop anesthesia controller tested in human volunteers and published in the Journal of Machine Learning Research. He designed and FPGA-validated a 32-bit RISC-V system-on-chip that runs FreeRTOS, and he was co-principal investigator on a NIST award on privacy-preserving synthetic data. He has been an investigator on more than $5.4 million in funded research from NSF, NASA and the U.S. Navy, and his publications have been cited more than 1,000 times.
He is the author of three Elsevier textbooks: Modern Assembly Language Programming with the ARM Processor (2016, second edition 2025) and ARM 64-bit Assembly Language (2019, with William Ughetta). From 2023 to 2026 he coordinated ABET accreditation for the Computer Science, Computer Engineering and Electrical Engineering programs, and he led the redesign of the Computer Engineering curriculum. As coach, he led Mines programming teams to first place in the ACM ICPC North Central North America regional and to honorable mention at the ICPC World Finals in 2018 and 2019.
Research Expertise
Reinforcement learning; planning under uncertainty and partially observable Markov decision processes (POMDPs); neural networks and spiking neural networks; computer architecture and RISC-V processor design; field-programmable gate arrays (FPGAs) and reconfigurable computing; hardware for machine learning; embedded and real-time systems; applications to robotics, medicine and cybersecurity.
Teaching
Dr. Pyeatt has taught all of the introductory and sophomore courses in Computer Science and Computer Engineering. He regularly teaches the upper-level Computer Engineering courses, including digital systems, assembly language, computer architecture, microprocessor design, operating systems and real-time operating systems, and occasionally teaches graduate courses in artificial intelligence, machine learning and computer engineering. He maintains the university's LaTeX class for theses and dissertations and helps graduate students use it.