Learning Ultra-Lean Classifiers with Structured Functions and Binary Lifting
![](https://deepdrive.berkeley.edu/sites/default/files/styles/project_primary/public/projects/Screen%20Shot%202020-07-21%20at%2012.08.02%20PM.png?itok=SuB3Hm6Y&c=0790aa2c8a286f5a0137871d59ba2aee)
ABOUT THIS PROJECT
At a glance
PRINCIPAL INVESTIGATORS | RESEARCHERS | THEMES |
---|---|---|
Stella Yu | model compression, manifold learning, complex-valued deep learning, binary lifting |
Deploying classifiers optimally learned offline from big data requires model compression and quantization, often with lossy performance and yet not enough compression. Our idea is to train a lean structured model to begin with, by building in the type of invariance the data/task desires, the type of layer functions that enforces sharing, and by delivering a binary representation that can be executed using logic-only operations. An ultra-lean classifier can thus be efficiently learned from the start to the end and deployed with far fewer MACs than a conventional deep classifier network.