Credits: 3
An introduction to the design and deployment of machine learning models optimized for edge devices and energy-efficient hardware accelerators. The course covers advanced model reduction techniques, such as quantization and pruning, to streamline complex models for deployment onresource-constrained platforms. Students will gain hands-on experience with Cadence Virtuoso to build circuits and systems that leverage in-memory computing architectures, facilitating efficient computation and reduced energy consumption.
Description
Prerequisites: Minimum grade of C- in ENEE303 or ENEE304.An introduction to the design and deployment of machine learning models optimized for edge devices and energy-efficient hardware accelerators. The course covers advanced model reduction techniques, such as quantization and pruning, to streamline complex models for deployment onresource-constrained platforms. Students will gain hands-on experience with Cadence Virtuoso to build circuits and systems that leverage in-memory computing architectures, facilitating efficient computation and reduced energy consumption.
Semesters Offered
Fall 2025
Testudo