Efficient Search Design for Hyperdimensional Computing
Brain-inspired hyperdimensional (HD) computing emulates cognition tasks by computing with hypervectors as an alternative to computing with numbers. At its very core, HD computing is about manipulating and comparing large patterns, stored in memory as hypervectors: the input symbols are mapped to a hypervector and an associative search is performed for reasoning and classification. For every classification event, a search module is in charge of finding the closest match between a set of “learned” hypervectors and a query hypervector by using a distance metric. When the dimensionality of hypervectors is in the thousands (e.g.,100,000 bits), an efficient search operation is challenging.
In this project, your goal would be to design an efficient and general module for search operations in HD computing. You would develop RTL implementation with FPGA prototyping.
- Looking for 1-2 Semester/Master students
- Contact: Abbas Rahimi
- HDL coding
- Architecture Design
- VLSI I
- 20% Theory
- 40% Architecture Design
- 40% Prototyping