Cory Merkel Headshot

Cory Merkel

Assistant Professor

Department of Computer Engineering
Kate Gleason College of Engineering
cemeec@rit.edu
585-475-4083
Office Location
GLE-3461

Cory Merkel

Assistant Professor

Department of Computer Engineering
Kate Gleason College of Engineering

Education

BS, MS, Ph.D., Rochester Institute of Technology

Bio

Dr. Cory Merkel joined the RIT computer engineering department in 2018. He earned his BS and MS degrees in computer engineering (2011) and a Ph.D. in microsystems engineering (2015), all from RIT. From 2016 to 2018, Dr. Merkel was a research electronics engineer with the Information Directorate, Air Force Research Lab. His current research focuses on mapping of AI algorithms, primarily artificial neural networks, to mixed-signal hardware and the design of brain-inspired computing systems using emerging technologies such as memristors. He has published his work in several peer-reviewed conferences, journals, and books, and is also engaged in a number of STEM outreach activities. For more information, see Dr. Merkel’s research website www.rit.edu/brainlab.

cemeec@rit.edu
585-475-4083

Select Scholarship

Journal Paper
Jha, Alexander Jones, Andrew Rush, Cory Merkel, Eric Herrmann, Ajey P. Jacobs, Clare Thiem, Rashmi. "A neuromorphic SLAM architecture using gated-memristive synapses." Neurocomputing 381. (2020): 89-104. Web.
Published Conference Proceedings
Fountain, Andrew and Cory Merkel. "Energy Constraints Improve Liquid State Machine Performance." Proceedings of the International Conference on Neuromorphic Systems. Ed. Catherine Schuman. N/A, United States: n.p., 2020. Web.
Merkel, Cory. "Exploring Energy-Accuracy Tradeoffs in AI Hardware." Proceedings of the International Green and Sustainable Computing Conference. Ed. Behrooz Shirazi. N/A, United States: n.p., 2020. Web.
Jones, Alex, et al. "A Segmented Attractor Network for Neuromorphic Associative Learning." Proceedings of the International Conference on Neuromorphic Systems. Ed. N/A. Knoxville, Tennessee: n.p., Web.
Merkel, Cory and Animesh Nikam. "A Low-Power Domino Logic Architecture for Memristor-Based Neuromorphic Computing." Proceedings of the International Conference on Neuromorphic Systems. Ed. N/A. Knoxville, Tennessee: n.p., Web.
Langroudi, Hamed, et al. "Exploiting Randomness in Deep Learning Algorithms." Proceedings of the International Joint Conference on Neural Networks. Ed. N/A. Budapest, Hungary: n.p., Web.
Merkel, Cory. "Current-Mode Memristor Crossbars for Neuromorphic Computing." Proceedings of the Neuro Inspired Computational Elements. Ed. N/A. Albany, New York: n.p., Web.

Currently Teaching

CMPE-630
Digital Integrated Circuit Design
3 Credits
This course will cover the basic theory and techniques of Digital Integrated Circuit Design in CMOS technology. Topics include CMOS transistor theory and operation, design and implementation of CMOS circuits, fabrication process, layout and physical design, delay and power models, static and dynamic logic families, testing and verification, memory and nanoscale technologies. Laboratory assignments and project facilitate in hands-on learning of circuit-level design and simulation, layout and parasitic extractions, pre and post-layout verification and validation, full-custom flow and Synthesis based flow, using industry standard CAD tools.
CMPE-530
Digital Integrated Circuit Design
3 Credits
This course will cover the basic theory and techniques of Digital Integrated Circuit Design in CMOS technology. Topics include CMOS transistor theory and operation, design and implementation of CMOS circuits, fabrication process, layout and physical design, delay and power models, static and dynamic logic families, testing and verification, memory and nanoscale technologies. Laboratory assignments and project facilitate in hands-on learning of circuit-level design and simulation, layout and parasitic extractions, pre and post-layout verification and validation, full-custom flow and Synthesis based flow, using industry standard CAD tools.
CMPE-765
Brain Inspired Computing
3 Credits
This course is primarily designed for graduate students and will expose them to theoretical and practical aspects of brain-inspired computing. It will offer students the opportunity to understand how the human brain computes to achieve intelligent behavior and how this understanding guides the development of new neural algorithms. We will identify the key developments and large issues at stake, and study brain inspired systems in the context of pragmatic applications. At the end of the course the students are expected to have expanded their knowledge of how the brain processes information, and how one can develop neuromorphic algorithms to tackle emergent spatio-temporal problems.
MATH-790
Research & Thesis
0 - 9 Credits
Masters-level research by the candidate on an appropriate topic as arranged between the candidate and the research advisor.

In the News

More News